CN116844152A - Method for realizing container storage yard container placement accuracy detection based on OCR technology - Google Patents
Method for realizing container storage yard container placement accuracy detection based on OCR technology Download PDFInfo
- Publication number
- CN116844152A CN116844152A CN202310690695.XA CN202310690695A CN116844152A CN 116844152 A CN116844152 A CN 116844152A CN 202310690695 A CN202310690695 A CN 202310690695A CN 116844152 A CN116844152 A CN 116844152A
- Authority
- CN
- China
- Prior art keywords
- attribute
- box
- box door
- value
- preset
- 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
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000005516 engineering process Methods 0.000 title claims abstract description 36
- 238000001514 detection method Methods 0.000 title claims abstract description 18
- 230000014509 gene expression Effects 0.000 claims abstract description 20
- 238000004458 analytical method Methods 0.000 claims description 73
- 238000012015 optical character recognition Methods 0.000 claims description 36
- 230000002159 abnormal effect Effects 0.000 claims description 31
- 238000007689 inspection Methods 0.000 claims description 16
- 238000012216 screening Methods 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 4
- 230000006698 induction Effects 0.000 claims description 4
- 238000012795 verification Methods 0.000 claims description 4
- 230000006399 behavior Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000005286 illumination Methods 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
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001568 sexual effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- GPRLSGONYQIRFK-MNYXATJNSA-N triton Chemical compound [3H+] GPRLSGONYQIRFK-MNYXATJNSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/35—Clustering; Classification
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- General Engineering & Computer Science (AREA)
- Character Discrimination (AREA)
Abstract
The invention discloses a method for realizing container placement accuracy detection of a container yard based on an OCR technology, and belongs to the technical field of container yards. The invention comprises the following steps: s1: uploading a box door photo by photographing a driver suitcase, and identifying box door text information by an OCR technology; s2: classifying the attribute of the box door text information according to the text position and the text rule by a text algorithm; s3: comparing the attribute values with regular expressions of preset attributes through rules of preset attribute values, and calculating whether the attribute values meet the rules or not. The invention solves the problems that most drivers with insufficient experience can not know whether the self suitcase is accurate or not, so that the accuracy of the suitcase is lost and the influence on the subsequent business is huge.
Description
Technical Field
The invention relates to the technical field of container yards, in particular to a method for detecting the accuracy of container placement in a container yard based on an OCR technology.
Background
The container yard puts the container according to the container putting instruction of the shipcompany or the agent thereof, and when the container yard is put to a customer, the relevant documents provided by the customer, such as a container loading list, an equipment handing-over list and the like, are checked, and the container yard is put to the corresponding empty container according with the requirements. Generally, when a driver drives a trailer to go to a container yard, the container yard checks the box condition according to a device handover list, and the container yard records suitcase information after box feeding: box number, suitcase license plate number, suitcase unit, etc. In the box checking link, a driver checks the box condition and only checks whether the box is damaged or abnormal, and most drivers with insufficient experience cannot know whether the box is accurate or not, and cannot judge whether the box type is correct or not, whether a shipcompany is correct or not and whether the box is special or not, so that the accuracy of the box is lost, and the influence on subsequent business is huge.
Disclosure of Invention
The invention aims to provide a method for detecting the container storage yard box-placing accuracy based on the OCR technology, which can effectively verify whether a ship company places boxes accurately, correct box-lifting errors in advance or even in time, improve the box-lifting accuracy, reduce the influence and loss caused by the box-lifting errors to a great extent and solve the problems in the background technology.
In order to achieve the above purpose, the present invention provides the following technical solutions:
the method for realizing container storage accuracy detection of the container yard based on the OCR technology comprises the following steps:
s1: uploading a box door photo by photographing a driver suitcase, and identifying box door text information by an OCR technology;
s2: after acquiring the box door text information, classifying attributes of the box door text information according to the text position and the text rule by a text algorithm, namely identifying a box number value, a ship company value, a box height value and a tare value;
s3: comparing the attribute values with regular expressions of preset attributes through rules of preset attribute values, calculating whether the attribute values meet the rules or not, pushing abnormal comparison analysis results to alarm service, and giving an alarm to each terminal.
Preferably, in the step S1, the driver' S suitcase is photographed and uploaded with a door photo, wherein the content of the door photo includes, but is not limited to, a ship company logo, an ultrahigh mark, a CSC nameplate, an ultrahigh warning plate, a qualified badge for inspection, a box number, a box size, a box code, a maximum total mass and empty box mass, a maximum payload and volume, an international railroad alliance mark, and an overweight mark.
Preferably, in the step S2, after obtaining the text information of the box door, the following operations are performed:
acquiring the box door text information, and converting the box door text information to a format which can be read by a computer;
acquiring converted box door text information, searching the box door text information, filtering out the box door text information which is not used for detecting the accuracy of container storage yard placement, and determining the box door text information which is used for detecting the accuracy of container storage yard placement;
the searched box door text information is obtained, the box door text information is classified, the box door text information is effectively classified according to a metering hierarchy classification method, and the attribute value of the box door is determined.
Preferably, in the step S3, the attribute value is compared with a regular expression of a preset attribute, and the following operations are performed:
acquiring a determined attribute value and a preset attribute value, and referring to the preset attribute value, comparing and analyzing the determined attribute value to determine a corresponding comparison and analysis result;
aiming at the condition that the determined attribute value is not in the range of the preset attribute value, determining that the comparison analysis result is that the box door is abnormal, pushing the abnormal comparison analysis result to an alarm service, and giving an alarm to each terminal;
aiming at the condition that the determined attribute value is in the range of the preset attribute value, the determined comparison analysis result is that the box door is normal, and the normal comparison analysis result is pushed to the system.
Preferably, in the step S3, the pushing of the abnormal comparison result to the alarm service, the alarm to each terminal, the following operations are performed:
determining corresponding early warning and alarming behaviors according to the comparison and analysis results;
establishing transmission links with all terminals, and acquiring the position information of a box door with abnormal box inspection in real time;
remotely transmitting the position information of the box door with abnormal box inspection to each terminal, and giving an alarm in real time;
and each terminal assigns the position of the box door where the staff goes to the abnormal box inspection box according to the received early warning and alarming information, and checks the box door box placement accuracy in real time, and the alarm is released after the box door inspection is finished.
Preferably, in the step S3, the rule of each attribute value is preset, the attribute value is compared with a regular expression of a preset attribute, and whether each attribute value meets the rule is calculated, wherein the calculation method for checking the bin number includes the following steps:
s311: converting the box main code into corresponding numbers;
s312: because the box main code, the equipment identification code and the box number are 10 bits in total, the equivalent number and the sequence number corresponding to the box main code are not X0, X1, X2. X9 once, and N is calculated according to the following formula:
s313: the check code divides the integer N of the above formula by 11 to obtain a remainder, and if the remainder is 10, the remainder is marked as 0 or the bin number is not needed.
Preferably, in the step S3, the rule of each attribute value is preset, the attribute value is compared with a regular expression of a preset attribute, and whether each attribute value meets the rule is calculated, wherein for the box verification method, the following operations are executed:
the load information that is equipped with the container on the chamber door includes: the total weight, the tare weight, the maximum payload and the volume of the load are subjected to OCR recognition and text attribute induction to obtain the load information of the tested container, the box type specification of the container is preliminarily obtained according to the load information, the ultrahigh warning board is arranged at the upper left side and the upper right side of the container, the ultrahigh mark is arranged on the left side box door, and whether the container is an ultrahigh box or not is obtained through a picture recognition technology.
Preferably, in the step S3, the rule of each attribute value is preset, the attribute value is compared with a regular expression of a preset attribute, and whether each attribute value meets the rule is calculated, wherein for the ship company information verification method, the following operations are executed:
the upper left side of the box door is provided with a container main mark, LOGO pictures of all container owners are preset in the system, the owner information of the checked containers is identified through OCR (optical character recognition) and picture identification technologies, and the information of the shipping company of the checked containers is obtained, wherein the first 4 digits of the container numbers are capital English letters, the first 3 digits of the letters are also the owner codes, and the owner information of the checked containers is judged through the owner code identification.
Preferably, in the step S1, in the process of photographing the suitcase of the driver and uploading the suitcase illumination, the following operations are performed to obtain the suitcase illumination, which specifically includes:
identifying the position of a box door, determining a target position, and locking a shooting area aiming at the target position;
according to the shooting area, shooting adjustment is carried out on the shooting device, a shooting photo is obtained, position analysis is carried out on the shooting device and the shooting area, the main direction of the shooting device is determined, the shooting device is further subjected to angle fine adjustment after being adjusted according to the determined main direction of the shooting device, and shooting is carried out after each angle fine adjustment, so that a plurality of initial shooting photos are obtained;
analyzing a plurality of initial photographing pictures, determining the areas of the same object in different initial photographing pictures, selecting one initial photographing picture from the initial photographing pictures as a basic picture, screening out the initial photographing pictures with the same area in the initial photographing pictures according to the same object area to obtain an object area screening result, and carrying out local area calibration on the basic picture according to the object area screening result to obtain a box door photo.
Preferably, when comparing and analyzing the determined attribute values, analyzing the attribute values with preset attribute values according to the attributes, and executing the following operations:
analyzing the attribute to determine an attribute type, wherein the attribute type comprises: the first type is the maximum value of the attribute, the range of the preset attribute value is smaller than the preset attribute value, the second type is the range of the preset attribute value, the range of the preset attribute value is in the range of the interval, the third type is the minimum value of the attribute, and the range of the preset attribute value is larger than the preset attribute value;
and carrying out comparison and analysis on the preset attribute value in combination with the preset attribute value according to the attribute type, and when the attribute belongs to the first type, carrying out comparison and analysis according to the following formula to obtain a comparison and analysis judgment value:
wherein G is i Comparison and analysis judgment value between attribute value representing i attribute and preset attribute value, and x i Attribute value representing i attribute, A i A preset attribute value representing i attribute;
when the attribute belongs to the second type, comparing and analyzing through the following formula to obtain a comparing and analyzing judgment value:
wherein G is j Comparison and analysis judgment value between attribute value representing j attribute and preset attribute value, and x j Attribute value representing j attribute, M j Representing the upper limit of a preset attribute value interval corresponding to the j attribute, N j Representing the lower limit of a preset attribute value interval corresponding to the j attribute;
when the attribute belongs to the third type, the comparison analysis is carried out through the following formula to obtain a comparison analysis judgment value:
wherein G is k Representing the genus of k-attributesComparing and analyzing judgment value between sexual value and preset attribute value, and x k Attribute value representing k attribute, B k A preset attribute value representing a k attribute;
and determining a comparison analysis result by referring to the analysis judgment value, wherein when the value of the comparison analysis judgment value is smaller than 0, the comparison analysis result is that the box door check box is normal, and when the value of the comparison analysis judgment value is not smaller than 0, the comparison analysis result is that the box door check box is abnormal.
Compared with the prior art, the invention has the beneficial effects that:
1. according to the invention, the box door text information is identified through OCR technology, after the box door text information is obtained, the attribute classification is carried out on the box door text information through a text algorithm according to the text position and the text rule, namely the box number value, the shipcompany value, the box height value and the tare weight value are identified, the rule of each attribute value is preset, the attribute value is compared with the regular expression of the preset attribute, whether each attribute value meets the rule is calculated, the result of comparison is abnormally pushed to an alarm service, and each terminal is alerted, so that whether the shipcompany is accurately placed or not can be effectively verified, the box error can be corrected in advance even timely, the box accuracy can be improved, and the influence and loss caused by the box error can be reduced to a great extent.
2. The invention can preliminarily check whether the information of the box number, the box type and the ship company is qualified or not by checking the information of the box number, the box type and the ship company, and prevent recording and transmission errors, wherein the box door is provided with the loading information of the container, and the invention comprises the following steps: the total weight, the tare weight, the maximum payload and the volume of the load are subjected to OCR recognition and text attribute induction to obtain the load information of the tested container, the box type specification of the container is preliminarily obtained according to the load information, the ultrahigh warning board is arranged at the upper left side and the upper right side of the container, the ultrahigh mark is arranged on the left side box door, and whether the container is an ultrahigh box or not is obtained through a picture recognition technology.
3. The invention presets LOGO pictures of all container owners in the system by arranging a container owner mark at the upper left of a box door, and recognizes the owner information of the checked container by OCR recognition and picture recognition technology to obtain the information of the company to which the container belongs, wherein the first 4 digits of the container number are capital English letters, the first 3 digits of the letters are also owner codes, and the owner information of the checked container is judged by the owner code recognition.
Drawings
FIG. 1 is a logic block diagram of a method of the present invention for achieving accuracy detection of container yard placement;
FIG. 2 is a flow chart of a method of the present invention for achieving accuracy detection of container yard placement;
FIG. 3 is an algorithm diagram of the present invention comparing attribute values to regular expressions of preset attributes.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In order to solve the existing box inspection link, a driver inspects the box condition and only inspects whether the box is damaged or abnormal, and most drivers with insufficient experience cannot know whether the self-carrying box is accurate or not, whether the box type is correct or not, whether a shipcompany is correct or not, and whether the special box is not or not, the accuracy of the carrying box is lost, the problem that the influence on the follow-up business is huge is solved, and referring to fig. 1-3, the following technical scheme is provided in the embodiment:
the method for realizing container storage accuracy detection of the container yard based on the OCR technology comprises the following steps:
s1: uploading a box door photo by photographing a driver suitcase, and identifying box door text information by an OCR technology;
s2: after acquiring the box door text information, classifying attributes of the box door text information according to the text position and the text rule by a text algorithm, namely identifying a box number value, a ship company value, a box height value and a tare value;
s3: comparing the attribute values with regular expressions of preset attributes through rules of preset attribute values, calculating whether the attribute values meet the rules or not, pushing abnormal comparison analysis results to alarm service, and giving an alarm to each terminal.
It should be noted that, by adopting the existing OCR technology and picture recognition technology, a complete set of box pattern model is designed through container door illumination, the core pixel point location is confirmed, the picture information of the tested box is identified and processed, so as to obtain accurate container information, and the problem that the box cannot be tested due to partial damage of the container door pattern of the container can be eliminated by combining a plurality of effective information.
Specifically, the box door text information is identified through OCR technology, after the box door text information is obtained, the box door text information is classified according to text positions and text rules through a text algorithm, namely, a box number value, a shipcompany value, a box height value and a tare value are identified, the attribute values are compared with regular expressions of preset attributes through rules of preset attribute values, whether the attribute values meet the rules is calculated, and the comparison and analysis result is abnormally pushed to an alarm service to alarm each terminal, so that whether the shipcompany is accurately placed or not can be effectively verified, the box errors can be corrected in advance and even timely, the box accuracy can be improved, and the influence and loss caused by the box errors can be reduced to a great extent.
In the step S1, a driver suitcase takes a photograph and uploads a suitcase photo, wherein the content of the suitcase photo comprises, but is not limited to, a ship company logo, an ultrahigh mark, a CSC nameplate, an ultrahigh warning sign, a qualified badge for inspection, a box number, a box size and a box code, a maximum total mass and empty box mass, a maximum payload and volume, an international railway alliance mark and an overweight mark.
It should be noted that the standard box number constitutes a basic concept: using the ISO6346 (1995) standard, the standard container number consists of an 11-bit code, comprising three parts: the first part is composed of 4-bit English letters, the first three-bit Code (Owner Code) mainly indicates the Owner and the operator of the container, the fourth bit Code indicates the type of the container, and the standard container listed as the beginning of CBHU indicates the Owner and the operator of the container to be far-away shipping; the second part consists of 6 digits, is a box registration code (Registration Code) and is used for a unique identifier held by a container body; the third part is Check code (Check Digit) which is obtained by the operation of Check rule by the first 4-bit letters and the 6-bit numbers and is used for identifying whether errors occur in Check, namely the 11 th Digit, the first three digits are the case east codes, the fourth Digit is mostly U, namely maritime, the TRU is the case of TRITON, the TCLU is the international case of TAL and the like.
In the step S2, after obtaining the text information of the box door, the following operations are executed:
acquiring the box door text information, and converting the box door text information to a format which can be read by a computer;
acquiring converted box door text information, searching the box door text information, filtering out the box door text information which is not used for detecting the accuracy of container storage yard placement, and determining the box door text information which is used for detecting the accuracy of container storage yard placement;
the searched box door text information is obtained, the box door text information is classified, the box door text information is effectively classified according to a metering hierarchy classification method, and the attribute value of the box door is determined.
The method comprises the steps of acquiring box door text information, converting the box door text information to a format which can be read by a computer, searching the box door text information, filtering out the box door text information which is not used for detecting the accuracy of container storage yard placement, determining the box door text information which is useful for detecting the accuracy of container storage yard placement, classifying the determined box door text information which is useful for detecting the accuracy of container storage yard placement, effectively classifying the box door text information according to a metering hierarchy classification method, and determining the attribute value of the box door.
In the step S3, the attribute value is compared with a regular expression of a preset attribute, and the following operations are executed:
acquiring a determined attribute value and a preset attribute value, and referring to the preset attribute value, comparing and analyzing the determined attribute value to determine a corresponding comparison and analysis result;
aiming at the condition that the determined attribute value is not in the range of the preset attribute value, determining that the comparison analysis result is that the box door is abnormal, pushing the abnormal comparison analysis result to an alarm service, and giving an alarm to each terminal;
aiming at the condition that the determined attribute value is in the range of the preset attribute value, the determined comparison analysis result is that the box door is normal, and the normal comparison analysis result is pushed to the system.
When the box door is detected to be abnormal, pushing an abnormal comparison analysis result to an alarm service, alarming to each terminal, establishing a transmission link with each terminal, acquiring the position information of the box door detecting the abnormal box door in real time, remotely transmitting the position information of the box door detecting the abnormal box door to each terminal, alarming in real time, assigning a worker to the position of the box door detecting the abnormal box door according to the received early warning alarm information, checking the box door box-placing accuracy in real time, and releasing the alarm after the box door detection is finished.
In the step S3, the result of the comparison and analysis is pushed to an alarm service, and the alarm service alarms to each terminal, and the following operations are executed:
determining corresponding early warning and alarming behaviors according to the comparison and analysis results;
establishing transmission links with all terminals, and acquiring the position information of a box door with abnormal box inspection in real time;
remotely transmitting the position information of the box door with abnormal box inspection to each terminal, and giving an alarm in real time;
and each terminal assigns the position of the box door where the staff goes to the abnormal box inspection box according to the received early warning and alarming information, and checks the box door box placement accuracy in real time, and the alarm is released after the box door inspection is finished.
In the step S3, comparing the attribute values with regular expressions of preset attributes through rules of preset attribute values, and calculating whether the attribute values meet the rules, wherein the calculation method for checking the box number comprises the following steps:
s311: converting the bin master code into the corresponding number, noting that there are no 11 and multiples thereof;
s312: because the box main code, the equipment identification code and the box number are 10 bits in total, the equivalent number and the sequence number corresponding to the box main code are not X0, X1, X2. X9 once, and N is calculated according to the following formula:
s313: the check code divides the formula integer N by the remainder obtained by 11, when the remainder is 10, the remainder is marked as 0 or the box number is not needed, the algorithm is preset in the system, the box number recognized by OCR is checked by the algorithm, and whether the box number is correct or not can be recognized.
Taking the case number "KKTU7452638" as an example, the ISO standard specifies that the affiliated Code (own Code) is identified by 3 uppercase latin letters, which mainly describes the case owner and operator; the equipment identification code indicates the type of the container, wherein 'U' represents the container, 'J' represents the container with the detachable equipment, 'Z' represents the trailer and the chassis frame, the number of the container is used for distinguishing different containers of the same container owner, the number of the container is composed of 6 Arabic numerals, the number of the container is less than 6, the number of the container is complemented by 0, the check code is used for preventing recording and transmission errors, the container number is identified through OCR, and whether the container number is qualified or not is primarily checked through a container number check rule.
In the step S3, comparing the attribute values with regular expressions of preset attributes through rules of preset attribute values, and calculating whether the attribute values meet the rules, wherein for a box type checking method, the following operations are executed:
the load information that is equipped with the container on the chamber door includes: the total weight, the tare weight, the maximum payload and the volume of the load are subjected to OCR recognition and text attribute induction to obtain the load information of the tested container, the box type specification of the container is preliminarily obtained according to the load information, the ultrahigh warning board is arranged at the upper left side and the upper right side of the container, the ultrahigh mark is arranged on the left side box door, and whether the container is an ultrahigh box or not is obtained through a picture recognition technology.
In the step S3, comparing the attribute values with regular expressions of preset attributes through rules of preset attribute values, and calculating whether the attribute values meet the rules, wherein for the ship company information verification method, the following operations are executed:
the upper left side of the box door is provided with a container main mark, LOGO pictures of all container owners are preset in the system, the owner information of the checked containers is identified through OCR (optical character recognition) and picture identification technologies, and the information of the shipping company of the checked containers is obtained, wherein the first 4 digits of the container numbers are capital English letters, the first 3 digits of the letters are also the owner codes, and the owner information of the checked containers is judged through the owner code identification.
In summary, the method for detecting the container storage yard box placement accuracy based on the OCR technology comprises the steps of photographing and uploading a box door photograph by a driver's suitcase, identifying box door text information by the OCR technology, acquiring the box door text information, classifying the box door text information according to text positions and text rules by a text algorithm, namely identifying a box number value, a ship company value, a box height value and a tare weight value, comparing the attribute values with regular expressions of preset attributes by preset rules of the attribute values, calculating whether the attribute values meet the rules, pushing abnormal comparison results to alarm service, and giving an alarm to each terminal, so that whether the container placement of the ship company is accurate can be effectively verified, the suitcase errors can be corrected in advance or even timely, the suitcase accuracy can be improved, and the influence and loss caused by the suitcase errors can be greatly reduced.
Further, in the step S1, in the process of uploading the door photograph by taking a photograph of the driver' S suitcase, the following operations are performed to obtain the door photograph, specifically as follows:
identifying the position of a box door, determining a target position, and locking a shooting area aiming at the target position;
according to the shooting area, shooting adjustment is carried out on the shooting device, a shooting photo is obtained, position analysis is carried out on the shooting device and the shooting area, the main direction of the shooting device is determined, the shooting device is further subjected to angle fine adjustment after being adjusted according to the determined main direction of the shooting device, and shooting is carried out after each angle fine adjustment, so that a plurality of initial shooting photos are obtained;
analyzing a plurality of initial photographing pictures, determining the areas of the same object in different initial photographing pictures, selecting one initial photographing picture from the initial photographing pictures as a basic picture, screening out the initial photographing pictures with the same area in the initial photographing pictures according to the same object area to obtain an object area screening result, and carrying out local area calibration on the basic picture according to the object area screening result to obtain a box door photo.
Above-mentioned through discernment chamber door position, confirm the target position, and the shooting region is locked to the target position makes shooting device can follow the container and carry out the chamber door and shoot, thereby avoid the driver's suitcase to shoot and upload the inconvenience of chamber door and shine, make easier acquisition chamber door and shine, further carry out the angle fine setting after adjusting shooting device according to the main direction of the shooting device of certainty, make shooting device can shoot under a plurality of bottoms and obtain a plurality of initial photographs of shooing, thereby avoid the influence of light to shooting the photograph, make the initial photograph of shooing that appears the same region can local regional calibration, improve the image effect of chamber door and shine, and then improve the accuracy of discernment and ensured the accuracy of chamber door text information.
Further, when comparing and analyzing the determined attribute values, analyzing the attribute values with preset attribute values according to the attributes, and executing the following operations:
analyzing the attribute to determine an attribute type, wherein the attribute type comprises: the first type is the maximum value of the attribute, the range of the preset attribute value is smaller than the preset attribute value, the second type is the range of the preset attribute value, the range of the preset attribute value is in the range of the interval, the third type is the minimum value of the attribute, and the range of the preset attribute value is larger than the preset attribute value;
and carrying out comparison and analysis on the preset attribute value in combination with the preset attribute value according to the attribute type, and when the attribute belongs to the first type, carrying out comparison and analysis according to the following formula to obtain a comparison and analysis judgment value:
wherein G is i Comparison and analysis judgment value between attribute value representing i attribute and preset attribute value, and x i Attribute value representing i attribute, A i A preset attribute value representing i attribute;
when the attribute belongs to the second type, comparing and analyzing through the following formula to obtain a comparing and analyzing judgment value:
wherein G is j Comparison and analysis judgment value between attribute value representing j attribute and preset attribute value, and x j Attribute value representing j attribute, M j Representing the upper limit of a preset attribute value interval corresponding to the j attribute, N j Representing the lower limit of a preset attribute value interval corresponding to the j attribute;
when the attribute belongs to the third type, the comparison analysis is carried out through the following formula to obtain a comparison analysis judgment value:
wherein G is k Comparing and analyzing judgment value, x, between attribute value representing k attribute and preset attribute value k Attribute value representing k attribute, B k A preset attribute value representing a k attribute;
and determining a comparison analysis result by referring to the analysis judgment value, wherein when the value of the comparison analysis judgment value is smaller than 0, the comparison analysis result is that the box door check box is normal, and when the value of the comparison analysis judgment value is not smaller than 0, the comparison analysis result is that the box door check box is abnormal.
In the above technical solution, in S3, the determined attribute value and the preset attribute value are obtained, the determined attribute value is compared and analyzed with reference to the preset attribute value, and when the corresponding comparison and analysis result is determined, the attribute value and the preset attribute value are analyzed according to the attribute, so that the attributes of different attribute types can be determined and compared with each other by adopting a unified standard, and the analysis result is determined by the formula And +.>And analyzing the attribute values of different attribute types in combination with preset attribute values to unify the attribute values of different attribute types, further determining comparison analysis results by adopting the same standard according to the reference analysis judgment values, providing convenience for determining corresponding comparison analysis results, pushing abnormal comparison analysis results to alarm service, and timely realizing alarm service.
It is noted that relational terms such as first and second, and the like are 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. Moreover, 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.
Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the principles and spirit of the invention, the scope of which is defined in the appended claims and their equivalents.
Claims (10)
1. The method for realizing the container storage accuracy detection of the container yard based on the OCR technology is characterized by comprising the following steps:
s1: uploading a box door photo by photographing a driver suitcase, and identifying box door text information by an OCR technology;
s2: after acquiring the box door text information, classifying attributes of the box door text information according to the text position and the text rule by a text algorithm, namely identifying a box number value, a ship company value, a box height value and a tare value;
s3: comparing the attribute values with regular expressions of preset attributes through rules of preset attribute values, calculating whether the attribute values meet the rules or not, pushing abnormal comparison analysis results to alarm service, and giving an alarm to each terminal.
2. The method for realizing container yard placement accuracy detection based on OCR technology according to claim 1, wherein the method comprises the following steps: in the step S1, a driver suitcase takes a photograph and uploads a suitcase photo, wherein the content of the suitcase photo comprises, but is not limited to, a ship company logo, an ultrahigh mark, a CSC nameplate, an ultrahigh warning sign, a qualified badge for inspection, a box number, a box size and a box code, a maximum total mass and empty box mass, a maximum payload and volume, an international railway alliance mark and an overweight mark.
3. The method for realizing container yard placement accuracy detection based on OCR technology according to claim 2, wherein the method comprises the following steps: in the step S2, after obtaining the text information of the box door, the following operations are executed:
acquiring the box door text information, and converting the box door text information to a format which can be read by a computer;
acquiring converted box door text information, searching the box door text information, filtering out the box door text information which is not used for detecting the accuracy of container storage yard placement, and determining the box door text information which is used for detecting the accuracy of container storage yard placement;
the searched box door text information is obtained, the box door text information is classified, the box door text information is effectively classified according to a metering hierarchy classification method, and the attribute value of the box door is determined.
4. The method for realizing container yard placement accuracy detection based on OCR technology according to claim 3, wherein the method comprises the following steps: in the step S3, the attribute value is compared with a regular expression of a preset attribute, and the following operations are executed:
acquiring a determined attribute value and a preset attribute value, and referring to the preset attribute value, comparing and analyzing the determined attribute value to determine a corresponding comparison and analysis result;
aiming at the condition that the determined attribute value is not in the range of the preset attribute value, determining that the comparison analysis result is that the box door is abnormal, pushing the abnormal comparison analysis result to an alarm service, and giving an alarm to each terminal;
aiming at the condition that the determined attribute value is in the range of the preset attribute value, the determined comparison analysis result is that the box door is normal, and the normal comparison analysis result is pushed to the system.
5. The method for realizing container yard placement accuracy detection based on OCR technology according to claim 4, wherein the method comprises the following steps: in the step S3, the result of the comparison and analysis is pushed to an alarm service, and the alarm service alarms to each terminal, and the following operations are executed:
determining corresponding early warning and alarming behaviors according to the comparison and analysis results;
establishing transmission links with all terminals, and acquiring the position information of a box door with abnormal box inspection in real time;
remotely transmitting the position information of the box door with abnormal box inspection to each terminal, and giving an alarm in real time;
and each terminal assigns the position of the box door where the staff goes to the abnormal box inspection box according to the received early warning and alarming information, and checks the box door box placement accuracy in real time, and the alarm is released after the box door inspection is finished.
6. The method for realizing container yard placement accuracy detection based on OCR technology according to claim 5, wherein the method comprises the following steps: in the step S3, comparing the attribute values with regular expressions of preset attributes through rules of preset attribute values, and calculating whether the attribute values meet the rules, wherein the calculation method for checking the box number comprises the following steps:
s311: converting the box main code into corresponding numbers;
s312: because the box main code, the equipment identification code and the box number are 10 bits in total, the equivalent number and the sequence number corresponding to the box main code are not X0, X1, X2. X9 once, and N is calculated according to the following formula:
s313: the check code divides the integer N of the above formula by 11 to obtain a remainder, and if the remainder is 10, the remainder is marked as 0 or the bin number is not needed.
7. The method for realizing container yard placement accuracy detection based on OCR technology according to claim 6, wherein the method comprises the following steps: in the step S3, comparing the attribute values with regular expressions of preset attributes through rules of preset attribute values, and calculating whether the attribute values meet the rules, wherein for a box type checking method, the following operations are executed:
the load information that is equipped with the container on the chamber door includes: the total weight, the tare weight, the maximum payload and the volume of the load are subjected to OCR recognition and text attribute induction to obtain the load information of the tested container, the box type specification of the container is preliminarily obtained according to the load information, the ultrahigh warning board is arranged at the upper left side and the upper right side of the container, the ultrahigh mark is arranged on the left side box door, and whether the container is an ultrahigh box or not is obtained through a picture recognition technology.
8. The method for realizing container yard placement accuracy detection based on OCR technology according to claim 7, wherein the method comprises the following steps: in the step S3, comparing the attribute values with regular expressions of preset attributes through rules of preset attribute values, and calculating whether the attribute values meet the rules, wherein for the ship company information verification method, the following operations are executed:
the upper left side of the box door is provided with a container main mark, LOGO pictures of all container owners are preset in the system, the owner information of the checked containers is identified through OCR (optical character recognition) and picture identification technologies, and the information of the shipping company of the checked containers is obtained, wherein the first 4 digits of the container numbers are capital English letters, the first 3 digits of the letters are also the owner codes, and the owner information of the checked containers is judged through the owner code identification.
9. The method for realizing container yard placement accuracy detection based on OCR technology according to claim 1, wherein the method comprises the following steps: in the step S1, in the process of photographing and uploading the door photo by the driver' S suitcase, the following operations are performed to obtain the door photo, which specifically includes:
identifying the position of a box door, determining a target position, and locking a shooting area aiming at the target position;
according to the shooting area, shooting adjustment is carried out on the shooting device, a shooting photo is obtained, position analysis is carried out on the shooting device and the shooting area, the main direction of the shooting device is determined, the shooting device is further subjected to angle fine adjustment after being adjusted according to the determined main direction of the shooting device, and shooting is carried out after each angle fine adjustment, so that a plurality of initial shooting photos are obtained;
analyzing a plurality of initial photographing pictures, determining the areas of the same object in different initial photographing pictures, selecting one initial photographing picture from the initial photographing pictures as a basic picture, screening out the initial photographing pictures with the same area in the initial photographing pictures according to the same object area to obtain an object area screening result, and carrying out local area calibration on the basic picture according to the object area screening result to obtain a box door photo.
10. The method for realizing container yard placement accuracy detection based on OCR technology according to claim 4, wherein the method comprises the following steps: when the determined attribute values are compared and analyzed, the attribute values are analyzed with preset attribute values according to the attributes, and the following operations are executed:
analyzing the attribute to determine an attribute type, wherein the attribute type comprises: the first type is the maximum value of the attribute, the range of the preset attribute value is smaller than the preset attribute value, the second type is the range of the preset attribute value, the range of the preset attribute value is in the range of the interval, the third type is the minimum value of the attribute, and the range of the preset attribute value is larger than the preset attribute value;
and carrying out comparison and analysis on the preset attribute value in combination with the preset attribute value according to the attribute type, and when the attribute belongs to the first type, carrying out comparison and analysis according to the following formula to obtain a comparison and analysis judgment value:
wherein G is i Comparison and analysis judgment value between attribute value representing i attribute and preset attribute value, and x i Attribute value representing i attribute, A i A preset attribute value representing i attribute;
when the attribute belongs to the second type, comparing and analyzing through the following formula to obtain a comparing and analyzing judgment value:
wherein G is j Comparison and analysis judgment value between attribute value representing j attribute and preset attribute value, and x j Attribute value representing j attribute, M j Representing j attribute pairsUpper limit of preset attribute value interval, N j Representing the lower limit of a preset attribute value interval corresponding to the j attribute;
when the attribute belongs to the third type, the comparison analysis is carried out through the following formula to obtain a comparison analysis judgment value:
wherein G is k Comparing and analyzing judgment value, x, between attribute value representing k attribute and preset attribute value k Attribute value representing k attribute, B k A preset attribute value representing a k attribute;
and determining a comparison analysis result by referring to the analysis judgment value, wherein when the value of the comparison analysis judgment value is smaller than 0, the comparison analysis result is that the box door check box is normal, and when the value of the comparison analysis judgment value is not smaller than 0, the comparison analysis result is that the box door check box is abnormal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310690695.XA CN116844152A (en) | 2023-06-12 | 2023-06-12 | Method for realizing container storage yard container placement accuracy detection based on OCR technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310690695.XA CN116844152A (en) | 2023-06-12 | 2023-06-12 | Method for realizing container storage yard container placement accuracy detection based on OCR technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116844152A true CN116844152A (en) | 2023-10-03 |
Family
ID=88166184
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310690695.XA Pending CN116844152A (en) | 2023-06-12 | 2023-06-12 | Method for realizing container storage yard container placement accuracy detection based on OCR technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116844152A (en) |
-
2023
- 2023-06-12 CN CN202310690695.XA patent/CN116844152A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11287391B2 (en) | Systems and methods for detecting threats and contraband in cargo | |
| CN101765853B (en) | Transportation and sorting system for identifying transport goods, particularly luggage items | |
| CN110238078B (en) | Sorting method, device, system and storage medium | |
| CN103996102B (en) | A kind of container body checking method | |
| CN109241986B (en) | Sample making method for rail transit vehicle part image recognition model | |
| CN110569864A (en) | vehicle loss image generation method and device based on GAN network | |
| CN115600941B (en) | Material management system of assembled prefabricated part factory | |
| CN117196437B (en) | Intelligent monitoring management system for logistics in intelligent park based on Internet of things | |
| CN113688965B (en) | Automatic storage code scanning detection method and cargo management system | |
| KR100931911B1 (en) | Monitoring method for entrance or exit of vehicle and system thereof | |
| CN202758396U (en) | Radio frequency identification apparatus and grain purchasing system | |
| KR102174424B1 (en) | Method for Inspecting Component basesd Server and system and apparatus therefor | |
| CN113361914B (en) | Dangerous waste transportation risk management and control early warning method and system | |
| CN116844152A (en) | Method for realizing container storage yard container placement accuracy detection based on OCR technology | |
| CN112100124A (en) | Container information automatic archiving method based on OCR recognition | |
| US20220366379A1 (en) | Intelligent monitoring system for waste disposal and method thereof | |
| CN113692172A (en) | Performance test cabinet of safety tool | |
| CN110414641A (en) | To the technical method of municipal solid waste incinerator garbage transporting vehicle compliance verifying | |
| CN115713758B (en) | Carriage identification method, system, device and storage medium | |
| CN112149660B (en) | Gun identification system | |
| CN117259219A (en) | Automatic detection system for PCB | |
| KR20240119872A (en) | Apparatus and method for automatically recognizing bonded truck in the port gate based on deep learning | |
| CN118505207A (en) | Full life cycle tracking management method for gas cylinder | |
| CN117763398A (en) | Method, equipment and program product for checking annotation data | |
| WO1992017287A2 (en) | Device to uniquely recognize travelling containers |
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 |