Data collection device, method, and program
The data collection device automates the detection of landmarks and event positions to improve the accuracy and efficiency of work log collection in heavy ion beam therapy systems, addressing the challenges of manual intervention and incomplete data acquisition.
Patent Information
- Application Number
- JP2024037535
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- Filing Date
- 2024-03-11
- Publication Date
- 2025-09-25
AI Technical Summary
Existing data collection methods for heavy ion beam adjustment in therapy systems lack accuracy due to the need for manual intervention and lack of integrated work log collection, leading to inconsistent and incomplete data acquisition.
A data collection device with a landmark detection unit, position setting unit, event detection unit, and data collection unit that automatically sets log collection ranges and event detection positions based on predefined landmarks, excluding exceptional images to ensure accurate data capture.
Enhances the accuracy and efficiency of work log collection by consistently determining log collection ranges and event detection positions, reducing manual intervention and improving data integrity.
Smart Images

Figure 2025138439000001_ABST
Abstract
Description
[Technical Field]
[0001] FIELD Embodiments of the present invention relate to a data collection device, method, and program. [Background technology]
[0002] In heavy ion therapy using a heavy ion therapy system, the heavy ion beam to be irradiated onto the affected area must be accurately aimed in advance to avoid damaging healthy tissue. For this reason, users make adjustments before treatment so that the beam is transported to the center of the treatment room. The beam position is controlled by electromagnets installed at multiple locations along the path from the accelerator to the treatment room. The beam accelerated by the accelerator is transported to the treatment room through a beam delivery pipe. Users check the position of the beam as it passes through the locations where the electromagnets are installed, and adjust the parameters of each electromagnet so that the beam passes through the center of the delivery pipe.
[0003] Typically, electromagnets are installed in 10 or more locations, so users have to visually adjust dozens of parameters. Adjustments are also required for each beam intensity and irradiation angle. For example, if the beam intensity can be adjusted in 600 steps and the beam angle can be adjusted in 360 steps, then 600 x 360 = 216,000 adjustments are required.
[0004] To reduce the burden on users, technology to automate beam adjustment is desired. To automate beam adjustment, it is necessary to collect work logs when users actually perform beam adjustment. However, typically, separate applications are used to adjust electromagnet parameters and to check the beam position, and these applications often do not have a built-in function for collecting work logs. This makes it difficult to effectively collect user work logs.
[0005] Furthermore, there is a data collection device that collects actual work data performed on a work terminal to automate beam adjustment. Such a data collection device can collect actual work data without modifying the work terminal, for example, by acquiring images displayed on the work terminal's display and analyzing the acquired images to collect work data.
[0006] With such data collection devices, if a user's operation intervenes during data collection, the data may not be collected properly. For example, if the window position or layout changes during work, the accuracy of image analysis will decrease. Also, since the user must decide the timing of data collection themselves, the collection accuracy will vary depending on the user's operation. [Prior art documents] [Patent documents]
[0007] [Patent Document 1] Patent No. 7174014 Summary of the Invention [Problem to be solved by the invention]
[0008] The problem to be solved by the present invention is to provide a data collection device, method, and program that improves the accuracy of collecting work logs. [Means for solving the problem]
[0009] To solve such problems, a data collection device according to an embodiment includes a landmark detection unit, a position setting unit, an event detection unit, and a data collection unit. The landmark detection unit detects landmarks from an input image. The position setting unit sets a log collection range or an event detection position based on a relative position of the landmark. The event detection unit detects an event at the event detection position. The data collection unit collects data within the log collection range when the event is detected. [Brief explanation of the drawings]
[0010] [Figure 1] FIG. 1 is a diagram showing an example of the configuration of a data collection device according to a first embodiment; [Figure 2] 10 is a flowchart illustrating a processing procedure of a data collection process according to the first embodiment; [Figure 3] FIG. 1 is a diagram showing a data flow in a data collection process according to the first embodiment; [Figure 4] FIG. 1 is a diagram showing an example of an input image according to the first embodiment; [Figure 5] Figure 4 shows the change in the display window position. [Figure 6] FIG. 10 is a diagram showing an example of an exceptional image according to the first embodiment; [Figure 7] FIG. 10 is a diagram showing an example of collected data according to the first embodiment; [Figure 8] FIG. 10 is a diagram showing an example of an input image according to a first modification of the first embodiment; [Figure 9] FIG. 10 is a diagram showing an example of an input image according to a second modification of the first embodiment; [Figure 10] FIG. 10 is a diagram showing an example of the configuration of a data collection device according to a second embodiment. [Figure 11] 10 is a flowchart illustrating a processing procedure of a data collection process according to a second embodiment; [Figure 12] FIG. 10 is a diagram showing a data flow in a data collection process according to a second embodiment. DETAILED DESCRIPTION OF THE INVENTION
[0011] Hereinafter, embodiments of a data collection device, a method, and a program will be described in detail with reference to the drawings. In the following description, components having substantially the same functions and configurations are designated by the same reference numerals, and redundant description will be given only when necessary.
[0012] (First embodiment) 1 is a diagram showing an example of the configuration of a data collection device 100 according to the first embodiment. The data collection device 100 is connected to a work terminal 200. The data collection device 100 and the work terminal 200 may be connected by wire, wirelessly, or via a network.
[0013] The work terminal 200 is a terminal device on which a worker performs predetermined work. The work terminal 200 includes an input interface such as a keyboard and a mouse, a console device with a processing circuit, a display, and the like. The work terminal 200 is, for example, a general PC terminal or a tablet terminal. The worker performs work using, for example, a predetermined application installed on the work terminal 200.
[0014] The work terminal 200 is, for example, a device for adjusting a heavy ion beam in a heavy ion beam therapy system. In this case, the worker starts, for example, a parameter input application and a beam observation application displayed on the display of the work terminal 200, and adjusts parameters using the parameter input application so that the beam distribution displayed in the beam observation application becomes a desired distribution.
[0015] The data collection device 100 collects work data from the work terminal 200. The data collection device 100 collects a work log of the work terminal 200 by continuously acquiring display images on the work terminal 200. The data collection device 100 is, for example, a general notebook PC terminal or tablet terminal. The work log is information about work performed using the work terminal 200. The work log includes, for example, an operation log, a parameter change history, and analysis results of the display image. The work log may also be called work data or collected data. The data collection device 100 may also be called a data collection unit.
[0016] The data collection device 100 is a computer having a processing circuit 11, a storage device 12, an input device 13, a communication device 14, and a display device 15. Data communication between the processing circuit 11, the storage device 12, the input device 13, the communication device 14, and the display device 15 is performed via a bus. The input device 13 and the display device 15 do not necessarily have to be provided.
[0017] The processing circuit 11 has a processor such as a CPU (Central Processing Unit) and a memory such as a RAM (Random Access Memory). The processing circuit 11 has a landmark detection unit 111, a position setting unit 112, an event detection unit 113, an exception determination unit 114, and a data collection unit 115. By executing a program, the processing circuit 11 realizes the landmark detection function, position setting function, event detection function, exception determination function, and data collection function of the above-mentioned units.
[0018] The storage device 12 is configured by a ROM (Read Only Memory), an HDD (Hard Disk Drive), an SSD (Solid State Drive), an integrated circuit storage device, etc. The storage device 12 stores programs and the like.
[0019] The program is stored in a non-transitory computer-readable recording medium such as the storage device 12. The program may be implemented as a single program that describes all the functions of each of the above-mentioned units, or as multiple modules divided into several functional units. Furthermore, each of the above-mentioned units may be implemented by an integrated circuit such as an Application Specific Integrated Circuit (ASIC). In this case, the units may be implemented in a single integrated circuit, or individually in multiple integrated circuits.
[0020] Various commands are input from an operator via the input device 13. A keyboard, a mouse, various switches, a touch pad, a touch panel display, etc. can be used as the input device 13. An output signal from the input device 13 is supplied to the processing circuit 11.
[0021] The communication device 14 is an interface for performing data communication with an external device connected to the data collection device 100 via a network. For example, the communication device 14 performs data communication with the work terminal 200.
[0022] The display device 15 displays various information. As the display device 15, a CRT (Cathode-Ray Tube) display, a liquid crystal display, an organic EL (Electro Luminescence) display, an LED (Light-Emitting Diode) display, a plasma display, or any other display known in the art can be appropriately used. The display device 15 may also be a projector.
[0023] Next, the functions executed by each unit of the processing circuit 11 will be described in detail. Landmark detection unit 111 detects landmarks from an input image input to work terminal 200. At this time, landmark detection unit 111 first continuously acquires image data of a display image displayed on the display of work terminal 200. At this time, the landmark detection unit 111 may acquire a display screen displayed on the display of work terminal 200, or may acquire an output signal output from a console device of work terminal 200 to the display in order to display the display screen on the display. Hereinafter, the image data acquired from work terminal 200 will be referred to as an input image.
[0024] Thereafter, the landmark detection unit 111 detects the positions of pre-specified landmarks in the input image. The landmarks are used to determine the log collection range and the event detection position. It is desirable that the positional relationship of the landmarks with the log collection range and the event detection position does not change even if the layout of the input image or the position of the application on the input screen changes, and that the landmarks are unique patterns in the input image. A unique pattern is a part of the input image that has a unique color or shape. For example, an icon or tab with a unique color or shape can be used as a landmark.
[0025] The log collection range is a region in the input image where data collection is performed and is a region used to collect a work log. The log collection range is, for example, a region where an image is captured. The log collection range may also be called a data collection range or a capture range. The log collection range is, for example, a region that includes a parameter display region in a parameter input application or a region that includes an energy distribution display region in a beam observation application.
[0026] The event detection position is a position where an event is detected to determine the timing to execute data collection. For example, a specific operation button or a display unit that displays a specific parameter can be used as the event detection position. For example, the occurrence of an event that changes a condition can be detected based on the icon of a specific operation button changing to an operated state. Furthermore, the occurrence of an event that adjusts a parameter can also be detected based on a change in the value of a parameter on a display unit that displays a specific parameter.
[0027] Landmark detection can be performed using, for example, a method using template matching or a filter response. The method using template matching is a method in which an image of a preset landmark is stored as a template, and a portion of the screen that matches the stored image is detected. The method using filter response is a method in which, when the shape of a landmark is known, a filter that reacts to the shape of the landmark is designed in advance, and the filter is applied to the image to detect the landmark from the screen. Note that multiple landmarks may be detected. For example, landmarks for setting the log collection range and landmarks for setting the event detection position may be detected separately.
[0028] The position setting unit 112 sets a log collection range and an event detection position based on the positions of the landmarks detected by the landmark detection unit 111. At this time, the position setting unit 112 sets the log collection range based on the relative position of the log collection range with respect to the landmark, and sets the event detection position based on the relative position of the event detection position with respect to the landmark. The positional relationship between the landmark and the log collection range, and the positional relationship between the landmark and the event detection position are set in advance by the user and stored in the storage device 12.
[0029] The event detection unit 113 detects an event at the event detection position. The event is used to determine the timing of collecting data. The event is, for example, a specific operation or a screen transition caused by a specific operation. Methods for detecting an event include, for example, a method for detecting a change in an image or a method for detecting a specific change pattern in an image.
[0030] The method of detecting changes in an image can be used when time-series information is collected by continuously acquiring input images. For example, the image pattern at the event detection position can be constantly stored, the difference between the previous image pattern and the current image pattern can be calculated, and an event can be determined to have occurred if the difference exceeds a threshold. Also, if the image pattern at the event detection position includes numbers or letters, the numbers or letters can be analyzed and stored, and changes in the numbers or letters can be detected as an event.
[0031] The method of detecting a specific image pattern can be used to detect an operation in which a specific image pattern is displayed. For example, the image pattern at the event detection position is compared with a pre-stored specific image pattern, and if the image patterns match, it is determined that an event has occurred. For example, if a specific button is set as the event detection position and the image pattern of the selected button changes to a specific image pattern when the button is selected, it is possible to detect that the user has pressed the specific button on the display screen by detecting the occurrence of the image pattern of the selected button as an event.
[0032] The exception determination unit 114 analyzes the image in the log collection range at the time the event is detected and determines whether the image in the log collection range is an exception image. An exception image is data that is likely to result in an exceptional value or an outlier when the image in the log collection range is analyzed. For example, if another display unit is displayed above the log collection range and the data display area to be collected is hidden by the other display unit, the image in the log collection range is determined to be an exception image. Examples of the other display unit include a window of another application, a file transfer dialog box, a pull-down menu, a parameter setting GUI, and a mouse cursor. Alternatively, image analysis may be used to detect characters or numbers in the image in the log collection range, and the image in the log collection range may be determined to be an exception image if no characters or numbers are displayed or if abnormal characters or numbers are displayed. Alternatively, a reference image may be stored in advance, and the similarity between the image in the log collection range and the reference image may be calculated. If the similarity is low, the image in the log collection range may be determined to be an exception image.
[0033] The data collection unit 115 collects data within the log collection range at the time the event was detected. At this time, the data collection unit 115 excludes images determined to be exceptional images by the exception determination unit 114, and collects only images that were not determined to be exceptional images. The collected images are stored in the storage device 12, for example.
[0034] The data collection unit 115 may collect the results of image analysis of the collected images. For example, it may collect letters and numbers obtained by image analysis, or may collect the results of analyzing the positions, distribution, shapes, etc. of objects in the images.
[0035] (Data collection and processing) Next, the operation of the data collection process executed by the data collection device 100 will be described. FIG. 2 is a flowchart showing an example of the procedure of the data collection process. FIG. 3 is a diagram showing an example of the flow of data in the data collection process. Note that the processing procedures in each process described below are merely examples, and each process can be modified as appropriate as possible. Furthermore, steps in the processing procedures described below can be omitted, replaced, or added as appropriate depending on the embodiment.
[0036] Here, a case where a work log of work using a beam confirmation application is collected will be described. The work terminal 200 is a terminal that uses a beam observation application to observe a heavy ion beam passing near each electromagnet of a heavy ion beam therapy device, and a case where the energy distribution of the heavy ion beam is collected using the data collection device 100 will be described as an example. The data collection process is performed with the data collection device 100 connected to the work terminal 200.
[0037] 4 and 5 are diagrams showing an example of an input image A1 acquired from the work terminal 200. The input image A1 is a display image output to the display of the work terminal 200. In the examples of FIGS. 4 and 5, a display window B1 of a beam observation application is displayed in the input image A1. FIG. 5 shows a state in which the position of the display window B1 has changed from the state shown in FIG. 4.
[0038] Here, the beam energy distribution display area (hereinafter referred to as the energy distribution display area) C1 is set as the log collection range, and the beam analysis result display area (hereinafter referred to as the analysis result display area) D1 is set as the event detection position. The energy distribution display area C1 displays the energy distribution of the beam passing near the selected electromagnet. The analysis result display area D1 displays the position coordinates and size of the beam's center of gravity as the analysis result of the beam displayed in the energy distribution display area C1. For example, the horizontal and vertical sizes are displayed as the beam size. The display in the analysis result display area D1 is updated every time the beam in the energy distribution display area C1 is updated.
[0039] In addition, a specific icon E1 in the beam observation application is set as a landmark. The icon E1 used as a landmark has a unique shape that differs from other parts in the display window B1. The icon E1 is, for example, a camera icon. As shown in FIGS. 4 and 5, even if the position of the display window B1 of the beam observation application on the display screen A changes, the relative position of the icon E1 with respect to the energy distribution display section C1 and the analysis result display section D1 does not change.
[0040] (Step S101) When the data collection process starts, landmark detection unit 111 continuously acquires, from work terminal 200, image data of input image A1 to be displayed on the display of work terminal 200. The acquired image data is used as the input image.
[0041] (Step S102) The landmark detection unit 111 detects an icon E1 set as a landmark by image analysis of the input image.
[0042] (Step S103) Next, the position setting unit 112 reads out the relative positions of the energy distribution display unit C1 and the analysis result display unit D1 with respect to the icon E1, and determines the positions of the energy distribution display unit C1 and the analysis result display unit D1 based on the position of the icon E1 detected in step S102 and the read-out relative positions.
[0043] Thereafter, the position setting unit 112 sets the energy distribution display section C1 as the log collection range, and sets the analysis result display section D1 as the event detection position.
[0044] (Step S104) Next, the event detection unit 113 continuously performs image analysis on the analysis result display area D1 set as the event detection position and determines whether or not an event has occurred based on the analysis results. When the coordinates or size of the center of gravity of the beam displayed in the analysis result display area D1 change due to a change in parameters related to the electromagnet, the event detection unit 113 detects the change in the beam as an event.
[0045] (Step S105) If an event is detected (step S104-Yes), the exception determination unit 114 determines whether or not the image in the energy distribution display unit C1 set as the log collection range for the input image in which the event was detected is an exceptional image. For example, as shown in Fig. 6, if a display window F of another application overlaps on the energy distribution display unit C1, the exception determination unit 114 determines that the image in the energy distribution display unit C1 is an exceptional image that is not appropriate as collection data.
[0046] (Step S106) If an event is detected (step S104-Yes) and the image of the energy distribution display section C1 in the input image in which the event was detected is not an exceptional image (step S105-No), the data collection unit 115 saves the image of the energy distribution display section C1 in the input image in which the event was detected as data in the log collection range.
[0047] The data collecting unit 115 also performs image analysis on the saved image of the energy distribution display unit C1 to calculate the center of gravity and size of the beam. The data collecting unit 115 then saves the analysis results for each input image. FIG. 7 is a diagram showing how the analysis results of the image of the energy distribution display unit C1 are saved. In FIG. 7, for each event that is not determined to be an exceptional image, the X-axis coordinate "x" of the center of gravity of the beam, the Y-axis coordinate "y" of the center of gravity of the beam, the X-axis coordinate "sx" of the beam size, and the Y-axis coordinate "sy" of the beam size. In addition, in FIG. 7, the above analysis results (x, y, sx, sy) are saved for each electromagnet to be adjusted.
[0048] (Step S107) The processing circuitry 11 repeatedly executes the processes of steps S101 to S106 described above until the work using the beam observation application on the work terminal 200 is completed (step S107-No), and continuously collects the image of the energy distribution display unit C1 at the time of the event occurrence as work data. Then, when the work using the beam observation application is completed (step S107-No), the processing circuitry 11 and the data collection device 100 end the series of data collection processes.
[0049] The effects of the data collection device 100 according to this embodiment will be described below.
[0050] If the work terminal 200 performing beam adjustment is a versatile device such as a PC, the location on the screen where the work log should be collected or the location to focus on for detecting screen changes may change depending on the user's operation. The display window of the collection target may also be hidden by the display window of another application. In these cases, data collection may fail. Furthermore, it is preferable to use values or beam shapes that change in response to changes in the situation as event detection positions for determining the timing of data collection. However, because the values and beam shapes are constantly changing, it is difficult to directly detect them through image analysis.
[0051] The data collection device 100 according to this embodiment is connected to a work terminal 200 equipped with a display. The data collection device 100 includes a landmark detection unit 111, a position setting unit 112, an event detection unit 113, an exception determination unit 114, and a data collection unit 115. The landmark detection unit 111 detects landmarks from an input image. The input image is a display image displayed on the display of the work terminal 200. The input image includes a display window displaying a log collection range, an event detection position, and landmarks. The display window may be, for example, a display window for a parameter input application for a heavy ion radiotherapy device or a display window for a beam observation application. The log collection range includes, for example, a display area for a work log, such as an adjustment target or parameter. An event may be, for example, a change in the log collection range. The relative positions of landmarks with respect to the log collection range and the event detection position do not change depending on the position of the display window in the input image. In other words, a portion whose relative position with respect to the log collection range and the event detection position does not change even if the position of the application display window changes can be used as a landmark. For example, a portion with a distinctive color or shape in the input image can be used as a landmark.
[0052] The position setting unit 112 sets a log collection range and an event detection position based on the relative position of the landmark. The event detection unit 113 detects an event at the event detection position. The data collection unit 115 collects image data within the log collection range when an event is detected. At this time, the data collection unit 115 may perform image analysis on the log collection range and collect the analysis results.
[0053] With the above configuration, the data collection device 100 according to this embodiment can detect landmarks from the input image output from the work terminal 200 and determine the log collection range and event detection position using the relative position of the landmark, so that even if the layout or position of the application changes due to user operation, the log collection range and event detection position can be accurately determined, enabling efficient collection of work logs. Furthermore, by using landmarks with unique colors or shapes, landmarks can be easily detected from the input image.
[0054] Furthermore, the data collection device 100 according to this embodiment further includes an exception determination unit 114 that performs an exception value determination on image data within the log collection range, and the data collection unit 115 collects only image data that has not been determined to be an exception value. This configuration makes it possible to perform an exception value determination on images within the log collection range, and to collect work logs by removing images when the log collection range is hidden by other displays or when the log collection range is set incorrectly. This improves the accuracy of work log collection. Furthermore, the ability to exclude unnecessary work logs allows for a reduction in the volume of stored data and cost savings.
[0055] The positional relationship of the log collection range and the event detection position to the landmark may change depending on the magnification ratio of the display window. In this case, the magnification ratio of the display window may be determined from the size of the detected landmark, and the relative position may be corrected according to the magnification ratio.
[0056] Alternatively, only the log collection range may be set using landmarks. In this case, compared to when the log collection range is set without using landmarks, it is possible to prevent areas containing unintended images from being set as the log collection range, thereby improving the accuracy of work log collection. This makes it possible to reduce the amount of data stored and cut costs. Alternatively, only the event detection position may be set using landmarks. In this case, compared to when the event detection position is set without using landmarks, it is possible to more effectively detect changes in the log collection range, thereby improving the accuracy of work log collection. This makes it possible to reduce the amount of data stored and cut costs.
[0057] That is, according to the data collection device 100 of this embodiment, the detection position (log collection range or event detection position) for determining the collection range (collection position or collection timing) of the work log can be set based on the relative position to the landmark, thereby improving the accuracy of collecting the work log.
[0058] (First Modification) In the above embodiment, the case where a work log of a beam observation application is collected has been mainly described. In this modified example, the case where a work log of a parameter input application is collected will be described. In this modified example, the work terminal 200 is a terminal that changes parameters of each electromagnet of a heavy ion beam therapy device using the parameter input application, and collects parameters input by the user using the data collection device 100.
[0059] Fig. 8 is a diagram showing an example of input image A2 output to the display of work terminal 200 in this modified example. In the example of Fig. 8, input image A2 displays a display window B2 of a parameter input application.
[0060] Here, the parameter input section C2 for inputting parameters is set as the log collection range, and the operation button D2 for changing the parameters is set as the event detection position. The parameter input section C2 displays the setting values of each parameter related to the selected electromagnet. Each parameter displayed in the parameter input section C2 can be changed by user input. The operation button D2 is a setting button for setting the parameters input in the parameter input section C2. When the operation button D2 is selected, the current parameters are updated to the parameters displayed in the parameter input section C2, and the color or shape of the operation button D2 changes.
[0061] Furthermore, a specific tab E2 in the parameter input application is set as a landmark. The tab E2 used as a landmark has a unique color that is different from other parts in the display window B2. For example, only the tab E2 is displayed in black in the display window B2. As shown in FIG. 8, even if the position of the display window B2 of the parameter input application on the display screen A changes, the relative position of the tab E2 with respect to the parameter input section C2 and the operation button D2 does not change.
[0062] In this modification, in the process of step S104, the event detection unit 113 continuously executes a process of analyzing the image of the operation button D2 set as the event detection position and determining whether or not an event has occurred based on the analysis results. When the operation button D2 changes to a state indicating that an operation has been performed, the event detection unit 113 determines that the parameters related to the electromagnet have been updated, and detects the parameter update as an event.
[0063] Furthermore, in the processing of step S106, the data collection unit 115 saves the image of the parameter input section C2 in the input image in which the event was detected as data within the log collection range. At this time, the data collection unit 115 performs image analysis on the saved image of the parameter input section C2 to detect parameters, and saves the analysis results for each input image. This makes it possible to collect the updated parameters each time the operation button D2, which is a setting button, is selected and the parameters of the electromagnet are updated.
[0064] (Second Modification) In this modification, a case where work logs of both a beam confirmation application and a parameter input application are collected will be described. In this modification, an operator uses the work terminal 200 to change the parameters of each electromagnet of the heavy ion beam therapy device using the parameter input application, and observes the heavy ion beam passing near each electromagnet of the heavy ion beam therapy device using the beam observation application. The data collection device 100 collects the parameters set using the parameter input application and the energy distribution of the heavy ion beam when the parameters are updated.
[0065] Fig. 9 is a diagram showing an example of input image A3 output to the display of work terminal 200 in this modified example. In the example of Fig. 9, input image A3 displays a display window B1 of the observation application and a display window B2 of the parameter input application. Since the display window B1 of the observation application is the same as that described in Figs. 4 and 5, and the display window B2 of the parameter input application is the same as that described in Fig. 8, detailed description thereof will be omitted.
[0066] In this modification, in step S102, landmarks are detected from the input image A3. At this time, the landmark detection unit 111 determines that both the parameter input application and the beam confirmation application are displayed based on the fact that the processing circuit 11 has detected the icon E1 and the tab E2 as landmarks. Thereafter, in step S103, the energy distribution display section C1 and the parameter input section C2 are set as the log collection range, and the analysis result display section D1 and the operation button D2 are set as the event detection position.
[0067] Thereafter, in step S104, if the operation button D2 changes to a state indicating that an operation has been performed, it is determined that an event has occurred. In this case, in step S106, the data collection unit 115 saves the image of the parameter input section C2 and the parameter setting values obtained by image analysis.
[0068] Furthermore, when the operation button D2 is pressed and parameters are changed, the voltage of the electromagnet and the like gradually change, and a gradual change appears in the energy distribution display section C1 of the beam confirmation application, causing the coordinates and size of the center of gravity of the beam displayed in the analysis result display section D1 to change. In step S104, if the coordinates and size of the center of gravity of the beam displayed in the analysis result display section D1 change, it is determined that an event has occurred, and in step S106, the image of the energy distribution display section C1 and the position and size of the heavy ion beam obtained by image analysis are saved. At this time, the data acquisition unit 115 saves the position and size of the heavy ion beam obtained from the energy distribution display section C1 in association with the setting values of the parameters obtained from the parameter input section C2.
[0069] It should be noted that if the image in the energy distribution display section C1 or the image in the parameter input section C2 is determined to be an exceptional image in step S105, that image is not saved.
[0070] According to this modification, every time the parameters of the electromagnet are updated, the position and size of the heavy particle beam can be stored in association with the parameters.
[0071] Note that when an event is detected in either the beam confirmation application or the parameter input application, data may be collected simultaneously in both the beam confirmation application and the parameter input application. In this case, the event may be detected only in one of the beam confirmation application and the parameter input application.
[0072] (Second embodiment) A second embodiment will be described. This embodiment is a modification of the configuration of the first embodiment as follows. Descriptions of the same configuration, operation, and effects as those of the first embodiment will be omitted. In the first embodiment, preset landmarks were used. In this embodiment, landmarks are automatically set using an input image.
[0073] Fig. 10 is a diagram showing an example of the configuration of the data collection device 100 according to this embodiment. As shown in Fig. 10, the processing circuitry 11 further includes a landmark setting unit 116. The processing circuitry 11 further realizes a landmark setting function by executing a program.
[0074] The landmark setting unit 116 automatically sets landmarks based on an image for landmark setting (hereinafter referred to as a setting image). The setting image is an image of the same type as the input image, and is input by, for example, a user. The landmark setting unit 116 detects a unique pattern in the input setting image, and automatically sets the detected unique pattern as a landmark. Note that a group of images included in video data may be used as the setting image.
[0075] For example, landmarks can be set by taking advantage of the fact that the correlation between a unique pattern and other regions in the input image is low. In this case, the landmark setting unit 116 calculates the degree of uniqueness for each pixel in the setting image by averaging the inverse of the correlation with other positions, detects an area where pixels with a high degree of uniqueness are concentrated as a unique pattern, and sets the detected area as a landmark.
[0076] Alternatively, an area that is detected as the unique pattern and whose relative position relative to the specified log collection range and event detection position does not change may be set as a landmark. In this case, the user inputs multiple setting images in which the position of the application display window on the image changes, and specifies the log collection range and event detection position in each setting image. The landmark setting unit 116 detects an area in each setting image whose positional relationship with the log collection range and event detection position does not change and has a high degree of uniqueness, and sets the detected area as a landmark.
[0077] (Data collection and processing) Next, the operation of the data collection process executed by the data collection device 100 according to this embodiment will be described. Fig. 11 is a flowchart showing an example of the procedure of the data collection process. Fig. 12 is a diagram showing an example of the flow of data in the data collection process.
[0078] In this modified example, first, the user inputs a setting image into the data collection device 100. The landmark setting unit 116 acquires the input setting image (step S201), performs image analysis on the setting image, detects a unique pattern in the setting image, and sets the detected unique pattern as a landmark (step S202).
[0079] Thereafter, the automatically set landmarks are used by the processing of steps S203 to S209 to collect the work log of the work terminal 200. The processing of steps S203 to S209 is similar to the processing of steps S101 to S107 in FIG. 2, and therefore detailed description thereof will be omitted.
[0080] According to the data collection device 100 of this embodiment, work logs can be collected using automatically set landmarks without having to set icons or tabs suitable for the landmarks in advance, thereby reducing the burden on the user.
[0081] Thus, according to any of the above-described embodiments, it is possible to provide a data collection device, method, and program that improves the accuracy of collecting work logs.
[0082] The present invention is not limited to the above-described embodiments, and the components can be modified and embodied in practice without departing from the spirit of the invention. Furthermore, various inventions can be created by appropriately combining multiple components disclosed in the above-described embodiments. For example, some components may be omitted from all the components shown in the embodiments. Furthermore, components from different embodiments may be appropriately combined. [Explanation of symbols]
[0083] 100...data collection device, 11...processing circuit, 12...memory device, 13...input device, 14...communication device, 15...display device, 111...landmark detection unit, 112...position setting unit, 113...event detection unit, 114...exception judgment unit, 115...data collection unit, 116...landmark setting unit, 200...work terminal, A1, A2, A3...input image, B1, B2...display window, C1, C2...log collection range, D1, D2...event detection position, E1, E2...landmark.
Claims
1. a landmark detection unit that detects landmarks from an input image; a position setting unit that sets a log collection range or an event detection position based on a relative position with respect to the landmark; an event detection unit that detects an event at the event detection position; a data collection unit that collects data within the log collection range when the event is detected; A data collection device comprising:
2. an exception determination unit that performs an exception value determination on the images in the log collection range, the data collection unit collects only images that are not determined to be exceptional values; The data collection device of claim 1 .
3. the input image includes a display window that displays the log collection range, the event detection position, and the landmark; a relative position of the landmark with respect to the log collection range and the event detection position does not change depending on the position of the display window in the input image; The data collection device of claim 1 .
4. The landmark is a unique pattern having a specific color or shape in the input image. The data collection device of claim 3 .
5. the log collection range includes a display area for the work log; the event is a change in the log collection range; The data collection device of claim 1 .
6. The data collection unit performs image analysis on the log collection range and collects analysis results. The data collection device of claim 1 .
7. the data collection device is connected to a work terminal having a display; The input image is a display image displayed on a display of the work terminal. The data collection device of claim 1 .
8. further comprising a landmark setting unit that sets the landmark based on the input image, The data collection device of claim 1 .
9. a landmark detection unit that detects landmarks from an input image acquired from a heavy ion beam therapy device that irradiates heavy ion beams using electromagnets; a position setting unit that sets an area in which an energy distribution of the heavy ion beam in the vicinity of the electromagnet is displayed as a log collection range based on a relative position with respect to the landmark, and sets an area in which an analysis result of the heavy ion beam is displayed as an event detection position; an event detection unit that detects a change in the analysis result at the event detection position as an event; a data collection unit that analyzes an energy distribution of the heavy ion beam in the log collection range when the event is detected and collects the analysis result as data of the log collection range; A data collection device comprising:
10. a landmark detection unit that detects landmarks from an input image acquired from a heavy ion beam therapy device that irradiates heavy ion beams using electromagnets; a position setting unit that sets an area in which parameters related to the electromagnet are displayed as a log collection range based on a relative position with respect to the landmark, and sets an operation unit that is operated when the parameters are changed as an event detection position; an event detection unit that detects a change in the operation unit at the event detection position as an event; a data collection unit that, when the event is detected, collects the parameters displayed in the log collection range as data of the log collection range; A data collection device comprising:
11. an exception determination unit that performs an exception value determination on the images in the log collection range, the data collection unit collects only images that are not determined to be exceptional values; 11. The data collection device according to claim 9 or 10.
12. the input image includes a display window that displays the log collection range, the event detection position, and the landmark; a relative position of the landmark with respect to the log collection range and the event detection position does not change depending on the position of the display window in the input image; 11. The data collection device according to claim 9 or 10.
13. The landmark is a unique pattern having a specific color or shape in the input image.
13. The data collection device of claim 12.
14. a landmark detection unit detecting landmarks from an input image; a position setting unit setting a log collection range or an event detection position based on a relative position with respect to the landmark; an event detection unit detecting an event at the event detection position; a data collection unit collecting image data within the log collection range when the event is detected; A method for providing
15. On the computer, The function to detect landmarks from the input image, a function of setting a log collection range or an event detection location based on a relative position with respect to the landmark; detecting an event at the event detection location; a function of collecting image data within the log collection range when the event is detected; A program to achieve this.
Citation Information
Patent Citations
Operation system, processing system, operation method, and program
JP7174014B2