KR102342084B1 - X-Ray transmission image object recognition device and method - Google Patents

Abstract

The present invention relates to an X-ray transmission image object recognition apparatus and method, and the apparatus according to the present invention includes a conveyor belt for transporting cargo, a barcode scanner for recognizing a barcode of cargo, and a three-dimensional camera for acquiring a three-dimensional image of the cargo , an X-ray line scanner that acquires an X-ray line scan image of the cargo, a monitor that displays an X-ray image of the cargo, a speed sensor that measures the speed of the cargo movement on the conveyor belt, and the The X-ray line scanner's X-ray output is adjusted by retrieving cargo information using barcodes, and the X-ray line scanner's X-ray line scan interval ( interval) and synthesizing X-ray line scan images to generate an X-ray image of the cargo. and a control unit for recognizing and classifying whether an abnormal object is applied, and enlarging or reducing the X-ray image of the cargo according to the size of the cargo recognized through the three-dimensional camera and displaying it on the monitor. According to the present invention, there is an advantage in that it is possible to solve the structural problems of the existing large X-ray system introduced in Korea, increase the processing speed, and in particular minimize human error during X-ray reading.

Description

X-Ray transmission image object recognition device and method

The present invention relates to an X-ray transmission image object recognition apparatus and method.

Due to the recent increase in overseas direct purchases, various goods are being brought in and are rapidly increasing. Accordingly, due to the saturation of the express customs clearance manager directly operated by the Korea Customs Service, the operation is being consigned to private companies. Even if the operation is entrusted to a private company, some problems still exist.

1. Problem of shortage of X-ray (Ray) readers

Video readers are directly operated by the Korea Customs Service, but there is a problem with the supply and demand of manpower and there is a quota.

2. Problems with reading X-ray (Ray) images

The X-ray image is dependent on the reader's naked eye, and the reading time of one item is very short, up to 5 seconds, which is highly susceptible to human error. In particular, there is a significant difference in the work capabilities of skilled and unskilled workers, which may delay the handling of incoming shipments.

3. X-ray (Ray) image storage problem

The storage of X-ray (Ray) images is stipulated by the relevant domestic law to be stored for more than one year. The contents of image storage are cargo on X-rays, but most of them are operated with foreign X-ray equipment. In addition, not only the corresponding image is stored, but also images of other goods are stored on the left and right sides of the image, and another human error may occur by delivering this to the goods inspector.

4. Problems with X-ray (Ray) equipment

There is no domestic manufacturer of large-scale X-ray equipment, and X-ray equipment is used not only in the customs office of the Korea Customs Service, but also in personal carry-in inspections at stadiums, personal carry-on inspections at airports, confectionery/drinks, etc. in the manufacturing process of factories. It is being used in various ways, such as foreign material inspection, which leads to serious foreign currency outflow.

The current automatic X-ray classification system relies on the human eye of the image reader, which can lead to human error. This can lead to very large social problems that can arise from the distribution of goods that should not be distributed in Korea (drugs, firearms, swords, food, medicines, quarantine items, etc.). In addition, there is a problem in the amount of processing because the processing amount of the skilled and the unskilled is remarkably different.

The technical problem to be solved by the present invention is to provide an apparatus and method for recognizing an X-ray transmission image object capable of increasing processing speed while minimizing human error during X-ray reading.

An X-ray transmission image object recognition apparatus according to an embodiment of the present invention for solving the above technical problem obtains a conveyor belt for transporting cargo, a barcode scanner for recognizing a barcode of the cargo, and a three-dimensional image of the cargo a three-dimensional camera, an X-ray line scanner for acquiring an X-ray line scan image of the cargo, a monitor for displaying an X-ray image of the cargo, a speed sensor for measuring the speed of movement of the cargo on the conveyor belt, and the The X-ray output of the X-ray line scanner is adjusted by retrieving cargo information using the barcode of the cargo recognized by the barcode scanner, and the X-ray according to the cargo movement speed of the conveyor belt measured by the speed sensor -Adjust the X-ray line scan interval of the line scanner and synthesize the X-ray line scan image to generate an X-ray image of the cargo, and deep learning the generated X-ray image ( Deep-Learning) technique is applied to the applied artificial intelligence (AI) object classification algorithm to recognize and classify abnormal objects, and according to the size of the cargo recognized through the 3D camera, enlarge or and a control unit which is reduced and displayed on the monitor.

An X-ray transmission image object recognition method according to an embodiment of the present invention for solving the above technical problem, the step of recognizing the barcode of the cargo transported through the conveyor belt using a barcode scanner, using a three-dimensional camera to obtain a three-dimensional image of the cargo, adjusting the X-ray line scan interval of the X-ray line scanner according to the cargo movement speed of the conveyor belt measured by a speed sensor, and Obtaining an X-ray line scan image of the cargo while adjusting the X-ray output of an X-ray line scanner by searching for cargo information using the barcode of the cargo, synthesizing the X-ray line scan image to obtain the cargo generating an X-ray image of and enlarging or reducing the X-ray image of the cargo according to the size of the cargo recognized through the 3D camera and displaying the enlarged or reduced image on the screen.

According to the present invention, there is an advantage in that it is possible to solve the structural problems of the existing large X-ray system introduced in Korea, increase the processing speed, and in particular minimize human error during X-ray reading.

In addition, by manufacturing and distributing large-scale X-rays, which are not available in Korea, using deep-learning-based object detection technology, abnormal items are displayed on X-ray images and provided to readers to minimize human error. At the same time, it can support rapid business processing.

1 is a block diagram showing the configuration of an X-ray transmission image object recognition apparatus according to an embodiment of the present invention.
2 is a schematic diagram showing a partial configuration of an X-ray transmission image object recognition apparatus according to an embodiment of the present invention.

Then, with reference to the accompanying drawings, the embodiments of the present invention will be described in detail so that those of ordinary skill in the art can easily carry out the present invention.

1 is a block diagram illustrating the configuration of an X-ray transmission image object recognition apparatus according to an embodiment of the present invention, and FIG. 2 is a partial configuration of an X-ray transmission image object recognition apparatus according to an embodiment of the present invention. It is a schematic diagram shown.

1 , the X-ray transmission image object recognition apparatus according to the present invention includes a conveyor belt 110 , a primary object detection sensor 120a , a secondary object detection sensor 120b , a barcode scanner 130 , and 3 It may include a dimension camera 140 , an X-ray line scanner 150 , a speed sensor 160 , a control unit 170 , a storage unit 180 , and a display unit 190 .

Conveyor belt 110 may transport a cargo (Baggage) containing the object to be sorted.

The primary object detection sensor 120a and the secondary object detection sensor 120b detect that the cargo moving along the conveyor belt 110 passes through a predetermined position. For this, the primary object detection sensor 120a and the secondary object detection sensor 120b may use a depth sensor.

The barcode scanner 130 performs a function of scanning the barcode displayed on the cargo. It is desirable to ensure that the barcode of the cargo complies with international standards.

The three-dimensional camera 140 performs a function of photographing a three-dimensional image of the cargo moving along the conveyor belt 110 .

The X-ray line scanner 150 may acquire an X-ray image of the cargo moving along the conveyor belt 110 . The X-ray line scanner 150 may include a vertical line scanner 150a that acquires an X-ray image of the cargo in a vertical direction and a horizontal line scanner 150b that acquires an X-ray image of the cargo in a horizontal direction. .

The speed sensor 160 performs a function of measuring the moving speed of the conveyor belt 110 , thereby confirming the moving speed of the cargo.

The controller 170 controls the overall operation of the X-ray transmission image object recognition apparatus according to the present invention, and may be implemented using a general-purpose computer or a special-purpose computer.

The storage unit 180 may store various types of information and data related to the operation of the X-ray transmission image object recognition apparatus according to the present invention. The storage unit 180 may be implemented as a computer integrated with the control unit 170 , or may be implemented as a separate storage device or server.

The display unit 190 may display various information and data related to the operation of the X-ray transmission image object recognition apparatus according to the present invention on the screen, and may be implemented as a display device such as a monitor.

Hereinafter, an operating method of the X-ray transmission image object recognition apparatus will be described.

First, when the loaded cargo is moved by the conveyor belt 110 and recognized by the primary object detection sensor 120a, the control unit 170 scans the barcode displayed on the cargo through the barcode scanner 130 to recognize the cargo information. can The control unit 170 may scan the barcode of the cargo moving through the conveyor belt 110 to check the information of the article. It is desirable to ensure that the barcode of the cargo complies with international standards.

Meanwhile, the controller 170 may recognize the size of the cargo by calculating the volume (width x length x height) of the object sensed through the 3D camera 140 .

The control unit 170 may perform a cargo information search (eg: Customs Service manifestation list) through a barcode recognized through the barcode scanner 130 . The customs office manifest and the like may be stored in advance in the storage unit 180 .

And, the control unit 170 refers to the cargo information search and adjusts the output voltage of the X-ray generator of the X-ray line scanner 150 to adjust the sharpness according to the density (organic material, inorganic material, mixture, etc.) of the cargo. can do. The output voltage of the X-ray generator is adjustable in the range of 100~155kv, and it has the effect of reducing power consumption.

In addition, the control unit 170 may calculate the enlargement/reduction ratio according to the size of the cargo when the image is displayed on the reader's monitor ( ) through the cargo size recognition through the three-dimensional camera 140 .

Next, when cargo is detected by the secondary object detection sensor 120b , the controller 170 may acquire an X-ray line scan image of the cargo through the X-ray line scanner 150 . In order to control the X-ray throughput, the speed of the conveyor belt 110 is 13 m/minute by default, but can be adjusted from 5 to 100 m/minute. The control unit 170 may automatically adjust the X-ray line scan interval according to the speed of the conveyor belt 110 .

And when the control unit 170 generates an X-ray image by synthesizing the X-ray line scan image obtained through the X-ray line scanner 150, the conveyor belt 110 measured by the speed sensor 160 Images can be synthesized by considering the speed of The control unit 170 synthesizes the X-ray line scan images obtained from the point in time when the cargo is detected by the secondary object detection sensor 120b until the point in time when the cargo is not detected by the secondary object detection sensor 120b. An X-ray image can finally be generated.

The controller 170 may recognize an object by applying the generated X-ray image to an artificial intelligence (AI) object classification algorithm to which a deep-learning technique is applied. The object classification algorithm may be trained in advance to detect abnormal items such as drugs, firearms, swords, food, medicines, quarantine items, and the like.

In addition, the control unit 170 may automatically enlarge and reduce the size of the cargo according to the size of the monitor ( ) so that the reader can easily recognize the horizontal/vertical screen of the detected object and display it on the screen.

The X-ray transmission image object recognition device according to the present invention is used in the fields of all import and export cargo of the Korea Customs Service airport only, airport network inbound and outbound travelers and baggage searches, security access searches such as public offices (eg embassies, concert halls, stadiums, etc.), counter-terrorism, etc. can be applied Of course, it can be applied to other fields necessary for non-destructive abnormal object recognition.

The embodiments described above may be implemented by a hardware component, a software component, and/or a combination of the hardware component and the software component. For example, the apparatus, methods and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA) array), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions, may be implemented using one or more general purpose or special purpose computers. The processing device may execute an operating system (OS) and one or more software applications running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, although one processing device is sometimes described as being used, one of ordinary skill in the art will recognize that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that can include For example, the processing device may include a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as parallel processors.

Software may comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be any kind of machine, component, physical device, virtual equipment, computer storage medium or apparatus, to be interpreted by or to provide instructions or data to the processing device. , or may be permanently or temporarily embody in a transmitted signal wave. The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored in one or more computer-readable recording media.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc. alone or in combination. The program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like. The hardware devices described above may be configured to operate as one or more software modules to perform the operations of the embodiments, and vice versa.

As described above, although the embodiments have been described with reference to the limited drawings, those skilled in the art may apply various technical modifications and variations based on the above. For example, the described techniques are performed in an order different from the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

Claims (2)

conveyor belts for transporting cargo,
A barcode scanner that recognizes the barcode of the cargo;
A three-dimensional camera for obtaining a three-dimensional image of the cargo;
an X-ray line scanner that acquires an X-ray line scan image of the cargo;
a monitor displaying an X-ray image of the cargo;
a speed sensor for measuring the speed of movement of the cargo on the conveyor belt; and
The cargo information is retrieved using the barcode of the cargo recognized by the barcode scanner to adjust the X-ray output of the X-ray line scanner, and according to the cargo movement speed of the conveyor belt measured by the speed sensor, the Adjusting the X-ray line scan interval of the X-ray line scanner and synthesizing the X-ray line scan image to generate an X-ray image of the cargo, and deep learning the generated X-ray image (Deep-Learning) technique is applied to the applied artificial intelligence (AI) object classification algorithm to recognize and classify abnormal objects, and expand the X-ray image of the cargo according to the size of the cargo recognized through the 3D camera or a control unit that is reduced and displayed on the monitor
X-ray transmission image object recognition device comprising a. Recognizing the barcode of the cargo transported through the conveyor belt using a barcode scanner,
obtaining a three-dimensional image of the cargo using a three-dimensional camera;
The X-ray line scan interval of the X-ray line scanner is adjusted according to the cargo movement speed of the conveyor belt measured by the speed sensor, and cargo information is retrieved using the recognized barcode of the cargo. acquiring an X-ray line scan image of the cargo while adjusting the X-ray output of the line scanner;
generating an X-ray image of the cargo by synthesizing the X-ray line scan image;
Applying the generated X-ray image to an artificial intelligence (AI) object classification algorithm to which a deep-learning technique is applied to recognize and classify an abnormal object; and
Enlarging or reducing the X-ray image of the cargo according to the size of the cargo recognized through the 3D camera and displaying it on the screen
X-ray transmission image object recognition method comprising a.

Images