WO2023208214A1 - 一种仪表盘识别方法、识别装置、存储介质和计算机设备 - Google Patents

一种仪表盘识别方法、识别装置、存储介质和计算机设备 Download PDF

Info

Publication number
WO2023208214A1
WO2023208214A1 PCT/CN2023/091733 CN2023091733W WO2023208214A1 WO 2023208214 A1 WO2023208214 A1 WO 2023208214A1 CN 2023091733 W CN2023091733 W CN 2023091733W WO 2023208214 A1 WO2023208214 A1 WO 2023208214A1
Authority
WO
WIPO (PCT)
Prior art keywords
instrument panel
pointer
instrument
contour
line segment
Prior art date
Application number
PCT/CN2023/091733
Other languages
English (en)
French (fr)
Inventor
王赟
刘杰慧
Original Assignee
瞬联软件科技（北京）有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 瞬联软件科技（北京）有限公司 filed Critical 瞬联软件科技（北京）有限公司
Publication of WO2023208214A1 publication Critical patent/WO2023208214A1/zh

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/42—Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/42—Global feature extraction by analysis of the whole pattern, e.g. using frequency domain transformations or autocorrelation
    • G06V10/435—Computation of moments
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
    • G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/40—Extraction of image or video features
    • G06V10/48—Extraction of image or video features by mapping characteristic values of the pattern into a parameter space, e.g. Hough transformation
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V20/00—Scenes; Scene-specific elements
    • G06V20/50—Context or environment of the image
    • G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/02—Recognising information on displays, dials, clocks

Definitions

  • the invention relates to an instrument panel identification method, and also relates to a corresponding instrument panel identification device, storage medium and computer equipment, and belongs to the technical field of instrumentation.
  • an instrument panel is usually displayed on a display screen to facilitate user viewing.
  • the instrument panel or other information is displayed on a console of a car, which provides a good user experience.
  • the Hough circle detection method is often used to identify the instrument panel due to the closed curve characteristics of traditional instrument panels.
  • the primary technical problem to be solved by the present invention is to provide an instrument panel identification method.
  • Another technical problem to be solved by the present invention is to provide an instrument panel recognition device.
  • Another technical problem to be solved by the present invention is to provide a corresponding storage medium and computer equipment.
  • a dashboard recognition method including the following steps:
  • S2 Perform contour detection on the collected instrument image according to the preset recognition area to obtain the first instrument panel contour map, use the preset area quantile ratio to filter the first instrument panel contour map and output a map including multiple sub-contours.
  • the second dashboard contour map and obtain the centroid of each sub-contour;
  • S4 Obtain the circle center and radius of the second instrument panel contour map based on the preset contour information and the centroid of each sub-contour, and establish a rectangular coordinate system with the circle center as the coordinate origin.
  • the rectangular coordinate system includes four quadrants. ;
  • S6 Perform Hough line detection on the instrument image to obtain at least one first pointer line segment, perform pointer cleaning on the at least one first pointer line segment according to the preset pointer information and obtain a second pointer line segment, according to the second The position information of the second pointer line segment is obtained from the slope of the pointer line segment relative to the Cartesian coordinate system and the quadrant located in the Cartesian coordinate system.
  • the dashboard recognition method further includes the following steps:
  • S5 Obtain the upper boundary of the second instrument profile based on the centroid of each sub-profile, and verify the radius based on the upper boundary and center point of the second instrument profile.
  • S6 further includes:
  • the dashboard recognition method also includes:
  • S7 Perform optical character recognition on the instrument image to obtain the display data of the instrument panel, determine whether the display data is consistent with the pointer reading, and output the judgment result.
  • the dashboard recognition method also includes:
  • S1 Set the identification area, outline information and pointer information of the instrument panel according to the a priori information displayed on the instrument panel.
  • a dashboard recognition device including: an image acquisition device, an image processing device and a controller, wherein the controller is configured as:
  • the image processing device performs contour detection on the instrument image according to the preset recognition area to obtain the first instrument panel outline map, and uses the preset area quantile ratio to filter the first instrument panel outline map and output the following information:
  • the rectangular coordinate system includes four quadrants;
  • the image processing device performs Hough line detection on the instrument image to obtain at least one first pointer line segment, performs pointer cleaning on the at least one first pointer line segment according to preset pointer information and obtains a second pointer line segment, according to The position information of the second pointer line segment is obtained by the slope of the second pointer line segment relative to the Cartesian coordinate system and the quadrant located in the Cartesian coordinate system.
  • the controller is further configured as:
  • the method further includes a page switching device for switching the display content of the display screen, and the controller is further configured to switch the display content of the display screen through the page switching device.
  • the controller further includes a log unit for recording identification information, and the controller is further configured to record the judgment result through the log unit.
  • a computer-readable storage medium on which a computer program is stored.
  • the computer program is executed by a processor, the above-mentioned instrument panel recognition method is implemented.
  • a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor.
  • the processor executes the computer program, the above is implemented. Dashboard identification method.
  • the present invention performs contour detection on the instrument panel based on the uniform similarity characteristics of each sub-contour on the instrument panel to obtain the instrument panel outline, circle center and radius, and then identifies the instrument panel pointer through Hough line detection. And establish a rectangular coordinate system based on the center of the circle of the instrument panel outline, and obtain pointer information based on the slope and quadrant position information of the pointer relative to the rectangular coordinate system. It can identify various instrument panels, especially instrument panels without closed curves, and improve instrument panel recognition. While improving the accuracy, it further improves the generalization of dashboard recognition.
  • Figure 1 is a flow chart of a dashboard identification method provided by an embodiment of the present invention.
  • FIG. 2 is a schematic diagram of an instrument image used in one embodiment of the present invention.
  • Figure 3 is an outline view of the first instrument in an embodiment of the present invention.
  • Figure 4 is a schematic diagram of a rectangular coordinate system with the center of the circle of the second instrument outline as the coordinate origin in one embodiment of the present invention
  • FIG. 5 is a flow chart of a dashboard identification method provided by another embodiment of the present invention.
  • Figure 6 is a schematic diagram of an asymmetric instrument panel in an embodiment of the present invention.
  • FIG. 7 is a structural block diagram of a dashboard recognition device in one embodiment of the present invention.
  • Figure 8 is a schematic structural diagram of corresponding computer equipment in an embodiment of the present invention.
  • the first embodiment of the present invention discloses a dashboard recognition method, which at least includes the following steps:
  • S2 Perform contour detection on the collected instrument image according to the preset recognition area to obtain the first instrument panel contour map, use the preset area quantile ratio to filter the first instrument panel contour map and output a map including multiple sub-contours.
  • the second dashboard contour map and obtain the centroid of each sub-contour;
  • S4 Obtain the circle center and radius of the second instrument panel contour map based on the preset contour information and the centroid of each sub-contour, and establish a rectangular coordinate system with the circle center as the coordinate origin.
  • the rectangular coordinate system includes four quadrants. ;
  • S6 Perform Hough line detection on the instrument image to obtain at least one first pointer line segment, perform pointer cleaning on the at least one first pointer line segment according to the preset pointer information and obtain a second pointer line segment, according to the second The position information of the second pointer line segment is obtained from the slope of the pointer line segment relative to the Cartesian coordinate system and the quadrant located in the Cartesian coordinate system.
  • contour detection is performed on the instrument panel based on the uniform similarity characteristics of each sub-contour on the instrument panel to obtain the instrument panel outline, circle center and radius, and then the pointer of the instrument panel is identified through Hough line detection. And establish a rectangular coordinate system based on the center of the circle of the instrument panel outline, obtain pointer information based on the slope and quadrant position information of the pointer relative to the rectangular coordinate system, and be able to identify whether various instrument panels appear, especially instrument panels without closed curves. In improving instrumentation While improving the accuracy of dashboard recognition, it also further improves the generalization of dashboard recognition.
  • Figure 2 shows an instrument image of an in-vehicle speed instrument collected by an embodiment of the present invention.
  • the instrument image includes a non-closed circle instrument panel outline 1, a pointer 2 and a specific displayed value 3.
  • the instrument image is an image captured in real time of the content displayed on the display screen. It can be a test image during the vehicle production stage or an actual display image when the vehicle is driving. The present invention does not apply to this. Make specific limitations.
  • the specific identification process is as follows:
  • the instrument panel includes multiple sub-contours, such as the first sub-contour 101 identifying the stage scale and the second sub-contour 102 identifying the basic scale.
  • the contour has the characteristics of uniform similarity, and edge detection is used to detect the contour of the ROI area of the instrument image.
  • the first instrument panel contour image after image binarization as shown in Figure 3 is obtained, including the detected first sub-contour 101 and the second sub-contour 103.
  • contour identification is performed through the plane rectangular coordinate system calibrated by OpenCV. Specifically, the area of each sub-contour is obtained according to the zero-order distance, and the barycenter coordinates, that is, the center of mass, of each sub-contour are obtained according to the first-order distance. Then, based on the uniform characteristics of the instrument panel scale line contour, quantile points are extracted for contours whose area is not 0. In one embodiment of the present invention, data cleaning is performed based on the single-variable contour area. According to the characteristics of uniform similarity of each sub-contour of the instrument panel, the contours of the 1/4 to 3/4 quantile points are extracted to obtain the second instrument panel. Contour drawing.
  • the instrument panel recognition method further includes setting a recognition area of the instrument panel before performing outline recognition on the instrument image.
  • a recognition area is set to facilitate the identification of the instrument image, thereby improving the accuracy of the instrument panel recognition and reducing the instrument panel recognition time.
  • the left and right boundaries of each sub-contour are obtained according to the centroid of each sub-contour, and at the same time, based on the preset upper, lower, left and right boundary ranges of the instrument panel, the left and right boundaries of each sub-contour are obtained.
  • Obtain the left and right boundaries of the second instrument panel outline obtain the circle center of the second instrument panel outline, and then obtain the second instrument based on the circle center, left boundary and/or right boundary of the second instrument panel outline. The radius of the disk outline.
  • the left and right boundary sub-contours of the second instrument profile are obtained according to the left and right boundaries of each sub-contour.
  • a rectangular coordinate system is established with the center of the circle of the second instrument panel outline as the coordinate origin (0, 0), Including the x-axis and the y-axis, the rectangular coordinate system includes four quadrants, namely the first quadrant 10, the second quadrant 20, the third quadrant 30 and the fourth quadrant 40.
  • the dashboard recognition method also includes:
  • S5 Obtain the upper boundary of the second instrument profile based on the centroid of each sub-profile, and verify the radius based on the upper boundary and center point of the second instrument profile.
  • the instrument panel recognition method also includes the coordinates (x3, y3) of the upper boundary sub-contour of the second instrument contour diagram, using the upper boundary sub-contour and the center of the circle. The distance performs a regression test on the radius R obtained previously.
  • the instrument panel recognition method further includes setting the outline information of the instrument panel before obtaining the circle center and radius of the second instrument panel outline map.
  • the outline information is set to facilitate the identification of the instrument image.
  • the outline information includes the upper, lower, left and right boundary ranges of the instrument panel, which can improve the The accuracy of dashboard recognition reduces the dashboard recognition time.
  • the Hough line detection method is used to detect the pointer of the instrument panel.
  • the Hough straight line detection method is used to perform straight line detection on the instrument image to obtain a plurality of first pointer line segments, and each first pointer line segment is filtered according to the preset pointer information, for example, according to the preset pointer information
  • the distance threshold between the center of the circle and the pointer is used to judge each first pointer line segment.
  • the first pointer line segment is filtered; and then each first pointer line segment is judged based on the preset positional relationship between the pointer length and the center of the circle. The first pointer line segment is judged.
  • the first pointer line segment is judged whether one end of the first pointer line segment is within the outline of the instrument panel and whether the other end is outside the outline of the instrument panel. If satisfied, it indicates that the first pointer line segment is the pointer of the instrument. Otherwise, it will be judged.
  • the first pointer line segment is filtered; thereby obtaining the pointer of the instrument image, that is, the second pointer line segment.
  • the position information of the pointer is obtained according to the slope of the second pointer line segment relative to the rectangular coordinate system based on the center of the circle and the quadrant position of the second pointer line segment.
  • the second pointer line segment 2 is in the third quadrant 30 of the Cartesian coordinate system.
  • the angular position pointed by the second pointer line segment in the instrument panel can be obtained, for example
  • the second pointer line segment points to a position of 30 degrees relative to the zero scale line 210 of the meter.
  • the instrument panel recognition method further includes using Hough straight line
  • the detection method sets the pointer information of the instrument panel before detecting the pointer of the instrument panel.
  • the pointer information is set according to the a priori information of the instrument panel to be tested to facilitate the identification of the instrument image.
  • the pointer information includes the distance threshold from the center of the circle to the pointer, and the length of the pointer and the center of the circle. The positional relationship can improve the accuracy of the instrument panel recognition and reduce the instrument panel recognition time.
  • the pointer reading of the instrument panel in the instrument image is obtained according to a preset instrument panel mapping table and the location information.
  • the instrument panel identification method may also include a preset instrument mapping table.
  • the instrument mapping table includes a corresponding relationship between the scale and angular position of the instrument panel, and the specific reading of the second pointer line segment can be obtained according to the instrument mapping table and the position information.
  • the instrument panel is a symmetrical instrument panel, and the relationship between the pointer reading and the angle is:
  • N is the reading of the pointer
  • M is the range of the instrument panel
  • ⁇ is the angle between the pointer and the zero scale line 210
  • ⁇ is the angle between the zero scale line 210 of the instrument panel and the y-axis
  • the angle between the full scale line 220 and the y-axis, then 2 ⁇ is the angle between the zero scale line 210 and the full scale line 220 on the instrument panel
  • 360°-2 ⁇ is the angle corresponding to the pointer at full scale.
  • the initial angle of the zero scale line is ⁇
  • the corresponding angle when the pointer is at full scale is ⁇ .
  • N is the reading of the pointer
  • M is the measuring range of the automobile instrument
  • ⁇ is the angle between the current position of the pointer and the zero scale line
  • ⁇ - ⁇ is the distance between the zero scale line and the full scale line of the automobile instrument.
  • 360°-2 ⁇ is the angle corresponding to the pointer at full scale.
  • the dashboard recognition method also includes:
  • S7 Perform optical character recognition on the instrument image to obtain the display data of the instrument panel, determine whether the display data is consistent with the pointer reading, and output the judgment result.
  • an optical character recognition method is further used to identify the display data 3 in the instrument image, that is, the vehicle speed displayed on the display screen. For example, when the vehicle speed is 60km/h, according to The speed read by the recognized pointer is compared with the vehicle speed displayed on the display screen. If the two are consistent, the accuracy of the recognition of the displayed instrument image is further verified.
  • the embodiment of the present invention also includes verifying the speed of the recognized pointer read based on the vehicle speed read from the vehicle CAN interface and using the vehicle speed to verify the display speed of the optical character recognition. test, I won’t go into details here.
  • the identification of whether the instrument panel appears in the instrument image shown in Figure 2 is completed.
  • the instrument panel is contour detected to obtain the instrument panel outline, circle center and radius, and then Identify the pointer of the instrument panel through Hough straight line detection, and establish a rectangular coordinate system based on the center of the circle of the instrument panel outline.
  • the embodiment of the present invention takes a display screen displaying instrument information on a vehicle as an example for explanation. This is only to illustrate the instrument panel identification method of the present invention, and does not limit the application of the instrument panel identification method only to instruments on the vehicle display screen. Dashboard detection, this dashboard recognition method can be applied to the detection and identification of various dashboards, and has broad application prospects.
  • the second embodiment of the present invention also provides an instrument panel recognition device, as shown in Figure 7, including: an image acquisition device, an image processing device and a controller, wherein the controller is configured as:
  • the image processing device performs contour detection on the instrument image according to the preset recognition area to obtain the first instrument panel outline map, and uses the preset area quantile ratio to filter the first instrument panel outline map and output the following information:
  • the rectangular coordinate system includes four quadrants;
  • the image processing device performs Hough line detection on the instrument image to obtain at least one first pointer line segment, performs pointer cleaning on the at least one first pointer line segment according to preset pointer information and obtains a second pointer line segment, according to The second pointer line segment is relative to The slope of the Cartesian coordinate system and the quadrant located in the Cartesian coordinate system are used to obtain the position information of the second pointer line segment.
  • the instrument panel identification device uses an image acquisition device to collect instrument images of the instrument panel to be tested.
  • the image acquisition device is a camera, which collects instrument images in response to instructions from the controller and transmits them to the controller.
  • the image processing device is used for data processing and recognition of the instrument image. Specifically, it includes contour recognition of the instrument image, and detects and obtains the contour of the instrument panel based on the uniform similarity characteristics of the sub-contours of each scale on the instrument panel.
  • the controller determines the center and radius of the instrument panel based on the outline of the instrument panel, and establishes a rectangular coordinate system based on the center of the instrument panel to facilitate the identification of the pointer position of the instrument panel; finally, the image processing device performs Hough line detection on the instrument image, Filter the detected line segments, for example, by the distance threshold from the center of the circle to the pointer, and by filtering the line segments that do not meet the conditions through the positional relationship between the length of the pointer and the center of the circle, thereby determining the pointer, and based on the quadrant of the pointer and the position relative to the rectangular coordinate system The slope further obtains the position of the pointer. Please refer to the foregoing embodiments for specific implementations, which will not be described again here.
  • controller is further configured to:
  • the pointer reading is obtained according to the position of the pointer through the instrument panel mapping table, thereby completing the instrument panel reading identification.
  • the optical character recognition method is used to identify the display data of the instrument panel, and the data read out based on the recognized pointer is compared with the data displayed on the display screen. If the two are consistent, the accuracy of the recognition of the instrument image is further verified.
  • the instrument panel recognition device further includes a page switching device for switching the display content of the display screen, and the controller is further configured to: switch the display screen through the page switching device display content.
  • the display content of the display screen is switched through a page switching device that can trigger the switching of the display content of the display screen, for example, the display content of the display screen is switched from text information, image information or video information to an instrument panel. display, thereby facilitating the instrument panel recognition device to collect the instrument panel displayed on the display screen and identify the collected images.
  • the instrument panel recognition device collects and identifies the displayed content.
  • the outline of the instrument panel determines that the displayed content is not an instrument panel, exits the recognition, and waits to receive the information again. Recognize the collected images again, or issue a prompt message.
  • the dashboard should not be displayed. In this case, if the outline of the dashboard cannot be recognized, it will exit the recognition; if the outline of the dashboard is recognized, a prompt message will be issued.
  • the present invention does not specifically limit the page switching device. It can be a switching device connected to the display screen through a wired or wireless network, or a switching device connected through the CAN interface of the vehicle itself, so as to be able to realize the display content of the display screen. Switch to design principles and won’t go into details here.
  • the instrument panel identification device further includes a log unit for recording identification information, and the controller is further configured to record the judgment result through the log unit.
  • the results of instrument image recognition are recorded through the log unit, for example, the display data in the previous embodiment and the comparison results of the pointer readout data are recorded.
  • the present invention does not specifically limit the log unit. It can record the recognition results of the display screen by the instrument recognition device, and can also obtain the vehicle's operation records through the log interface connected to the vehicle, such as obtaining the sensing data of the vehicle sensor, etc. I won’t go into details here.
  • the third embodiment of the present invention provides a computer-readable storage medium in which a computer program is stored.
  • the computer program When executed by a processor, it implements: S2: Perform contour detection on the collected instrument image according to a preset recognition area to obtain The first dashboard outline map uses the preset area quantile ratio to filter the first dashboard outline map and outputs a second dashboard outline map including multiple sub-contours, and obtains the centroid of each sub-contour; S4: The center and radius of the second instrument panel outline are obtained according to the preset contour information and the centroid of each sub-contour, and a rectangular coordinate system is established with the center of the circle as the coordinate origin.
  • the rectangular coordinate system includes four quadrants; S6 : Perform Hough line detection on the instrument image to obtain at least one first pointer line segment, perform pointer cleaning on the at least one first pointer line segment according to preset pointer information and obtain a second pointer line segment, according to the second pointer
  • the position information of the second pointer line segment is obtained from the slope of the line segment relative to the Cartesian coordinate system and the quadrant located in the Cartesian coordinate system.
  • the computer-readable storage medium may use one or more computer Any combination of machine-readable media.
  • the computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium.
  • the computer-readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination thereof. More specific examples (non-exhaustive list) of computer readable storage media include: electrical connections having one or more conductors, portable computer disks, hard drives, random access memory (RAM), read only memory (ROM), Erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination of the above.
  • a computer-readable storage medium may be any tangible medium that contains or stores a program for use by or in connection with an instruction execution system, apparatus, or device.
  • a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave carrying computer-readable program code therein. Such propagated data signals may take many forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above.
  • a computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device .
  • Program code embodied on a computer-readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wire, optical cable, RF, etc., or any suitable combination of the foregoing.
  • Computer program code for performing the operations of the present invention may be written in one or more programming languages, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional A procedural programming language—such as "C" or a similar programming language.
  • the program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server.
  • the remote computer can be connected to the user's computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or it can be connected to an external computer (such as an Internet service provider through the Internet). connect).
  • LAN local area network
  • WAN wide area network
  • Internet service provider such as an Internet service provider through the Internet. connect
  • a fourth embodiment of the present invention provides a computer device 12.
  • the computer device 12 is in the form of a general computing device, the components of which may include but are not limited to: one or more processors or processing units 16, system memory 28, connecting different system groups bus 18 for components including system memory 28 and processing unit 16.
  • Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, a graphics accelerated port, a processor, or a local bus using any of a variety of bus structures.
  • these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect ( PCI) bus.
  • ISA Industry Standard Architecture
  • MAC Micro Channel Architecture
  • VESA Video Electronics Standards Association
  • PCI Peripheral Component Interconnect
  • Computer device 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by computer device 12, including volatile and nonvolatile media, removable and non-removable media.
  • System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and/or cache memory 32 .
  • Computer device 12 may further include other removable/non-removable, volatile/non-volatile computer system storage media.
  • storage system 34 may be used to read and write to non-removable, non-volatile magnetic media (not shown in Figure 8 and commonly referred to as a "hard drive”).
  • a disk drive may be provided for reading and writing to removable non-volatile disks (e.g., "floppy disks"), and for removable non-volatile optical disks (e.g., CD-ROM, DVD-ROM or other optical media) that can read and write optical disc drives.
  • each drive may be connected to bus 18 through one or more data media interfaces.
  • Memory 28 may include at least one program product having a set (eg, at least one) of program modules configured to perform the functions of embodiments of the invention.
  • a program/utility 40 having a set of (at least one) program modules 42 may be stored, for example, in memory 28 , each of these embodiments or some combination may include the implementation of a network environment.
  • Program modules 42 generally perform functions and/or methods in the described embodiments of the invention.
  • Computer device 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with computer device 12, and/or with Any device (eg, network card, modem, etc.) that enables the computer device 12 to communicate with one or more other computing devices. This communication may occur through input/output (I/O) interface 22. and, computer equipment 12 Communication with one or more networks, such as a local area network (LAN), a wide area network (WAN), and/or a public network, such as the Internet, may also be accomplished through network adapter 20. As shown in FIG. 8, network adapter 20 communicates with other modules of computer device 12 via bus 18.
  • I/O input/output
  • network adapter 20 communicates with other modules of computer device 12 via bus 18.
  • the processor unit 16 executes programs stored in the system memory 28 to perform various functional applications and data processing, for example, implementing a dashboard recognition method provided by the embodiment of the present invention.
  • the present invention performs contour detection on the instrument panel based on the uniform similarity characteristics of each sub-contour on the instrument panel to obtain the instrument panel outline, circle center and radius, and then identifies the instrument panel pointer through Hough line detection. And establish a rectangular coordinate system based on the center of the circle of the instrument panel outline, obtain pointer information based on the slope and quadrant position information of the pointer relative to the rectangular coordinate system, and be able to identify various instrument panel information, especially instrument panels without closed curves, in improving instrument panels While improving the accuracy of recognition, it further improves the generalization of dashboard recognition. Moreover, the present invention can be used to identify whether the instrument panel appears, so as to avoid erroneous display of the instrument panel.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Computing Systems (AREA)
  • Image Analysis (AREA)

Abstract

本发明公开了一种仪表盘识别方法、识别装置、存储介质和计算机设备。该仪表盘识别方法包括如下步骤：根据预先设置的识别区域对采集的仪表图像进行轮廓检测获得仪表盘轮廓图、圆心和半径，并以圆心为坐标原点建立包括四个象限的直角坐标系；对仪表图像进行霍夫直线检测获取至少一条第一指针线段，根据预先设置的指针信息进行指针清洗并获取第二指针线段，根据第二指针线段相对于直角坐标系的斜率、以及位于直角坐标系的象限获取第二指针线段的位置信息。利用本发明，能够辨别仪表盘是否出现，并能识别各种仪表盘信息，特别是没有闭合曲线的仪表盘，在提高仪表盘识别的准确性的同时，进一步提高仪表盘识别的泛化性。

Description

一种仪表盘识别方法、识别装置、存储介质和计算机设备 技术领域
本发明涉及一种仪表盘识别方法，同时涉及相应的仪表盘识别装置、存储介质和计算机设备，属于仪器仪表技术领域。
背景技术
现有技术中，通常在显示屏上显示仪表盘以便于使用者观看，例如，在汽车的控制台上显示仪表盘或其他信息，具有良好的用户使用体验。在实际检测中，针对传统仪表盘具有闭合曲线的特性多采用霍夫圆检测方法对仪表盘进行识别。然而，对于没有闭合曲线的仪表盘，存在无法识别的问题。
发明内容
本发明所要解决的首要技术问题在于提供一种仪表盘识别方法。
本发明所要解决的另一技术问题在于提供一种仪表盘识别装置。
本发明所要解决的又一技术问题在于提供一种相应的存储介质和计算机设备。
为了实现上述目的，本发明采用下述的技术方案：
根据本发明实施例的第一方面，提供一种仪表盘识别方法，包括如下步骤：
S2：根据预先设置的识别区域对采集的仪表图像进行轮廓检测获得第一仪表盘轮廓图，使用预先设置的面积分位比对所述第一仪表盘轮廓图进行滤波并输出包括多个子轮廓的第二仪表盘轮廓图，并获取各子轮廓的质心；
S4：根据预先设置的轮廓信息和各子轮廓的质心获取所述第二仪表盘轮廓图的圆心和半径，并以所述圆心为坐标原点建立直角坐标系，所述直角坐标系包括四个象限；
S6：对所述仪表图像进行霍夫直线检测获取至少一条第一指针线段，根据预先设置的指针信息对所述至少一条第一指针线段进行指针清洗并获取第二指针线段，根据所述第二指针线段相对于所述直角坐标系的斜率、以及位于所述直角坐标系的象限获取所述第二指针线段的位置信息。
其中较优地，在S4之后、S6之前，该仪表盘识别方法还包括如下步骤：
S5：根据各子轮廓的质心获取所述第二仪表轮廓图的上边界，并根据所述第二仪表轮廓图的上边界和圆心验证所述半径。
其中较优地，S6进一步包括：
根据预先设置的仪表盘映射表和所述位置信息获取所述仪表图像中仪表盘的指针读数。
其中较优地，在S6之后，该仪表盘识别方法还包括：
S7：对所述仪表图像进行光学字符识别获取所述仪表盘的显示数据，判断所述显示数据与所述指针读数是否一致并输出判断结果。
其中较优地，在S2之前，该仪表盘识别方法还包括：
S1：根据所述仪表盘显示的先验信息设置所述仪表盘的识别区域、轮廓信息和指针信息。
根据本发明实施例的第二方面，提供一种仪表盘识别装置，包括：图像采集装置、图像处理装置和控制器，其中，所述控制器配置为：
通过所述图像采集装置对显示屏进行图像采集并获取仪表图像；
通过所述图像处理装置根据预先设置的识别区域对所述仪表图像进行轮廓检测获得第一仪表盘轮廓图，使用预先设置的面积分位比对所述第一仪表盘轮廓图进行滤波并输出包括多个子轮廓的第二仪表盘轮廓图，并获取各子轮廓的质心；
根据预先设置的轮廓信息和各子轮廓的质心获取所述第二仪表盘轮廓图的圆心和半径，并以所述圆心为坐标原点建立直角坐标系，所述直角坐标系包括四个象限；
通过所述图像处理装置对所述仪表图像进行霍夫直线检测获取至少一条第一指针线段，根据预先设置的指针信息对所述至少一条第一指针线段进行指针清洗并获取第二指针线段，根据所述第二指针线段相对于所述直角坐标系的斜率、以及位于所述直角坐标系的象限获取所述第二指针线段的位置信息。
其中较优地，所述控制器进一步配置为：
根据预先设置的仪表盘映射表和所述位置信息获取所述仪表图像中仪表盘的指针读数；
对所述仪表图像进行光学字符识别获取所述仪表盘的显示数据，判断所述显示数据与所述指针读数是否一致并输出判断结果。
其中较优地，还包括用于切换所述显示屏显示内容的页面切换装置，所述控制器进一步配置为：通过所述页面切换装置切换所述显示屏的显示内容。
其中较优地，还包括用于记录识别信息的日志单元，所述控制器进一步配置为：通过所述日志单元记录所述判断结果。
根据本发明实施例的第三方面，提供一种计算机可读存储介质，其上存储有计算机程序，所述计算机程序被处理器执行时实现上述的仪表盘识别方法。
根据本发明实施例的第四方面，提供一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，所述处理器执行所述计算机程序时实现上述的仪表盘识别方法。
与现有技术相比较，本发明根据仪表盘上各子轮廓具有均匀相似性的特性对仪表盘进行轮廓检测以获取仪表盘轮廓、圆心和半径，再通过霍夫直线检测识别仪表盘的指针，并基于仪表盘轮廓的圆心建立直角坐标系，根据指针相对于直角坐标系的斜率和象限位置信息获取指针信息，能够识别各种仪表盘，特别是没有闭合曲线的仪表盘，在提高仪表盘识别的准确性的同时，进一步提高仪表盘识别的泛化性。
附图说明
图1为本发明的一个实施例提供的仪表盘识别方法的流程图；
图2为本发明的一个实施例中，使用的仪表图像的示意图；
图3为本发明的一个实施例中，第一仪表的轮廓图；
图4为本发明的一个实施例中，以第二仪表轮廓图的圆心为坐标原点的直角坐标系的示意图；
图5为本发明的另一个实施例提供的仪表盘识别方法的流程图；
图6为本发明的一个实施例中，非对称仪表盘的示意图；
图7为本发明的一个实施例中，仪表盘识别装置的结构框图；
图8为本发明的一个实施例中，相应的计算机设备的结构示意图。
具体实施方式
下面结合附图和具体实施例对本发明的技术内容进行详细具体的 说明。
如图1所示，本发明的第一实施例公开了一种仪表盘识别方法，至少包括如下步骤：
S2：根据预先设置的识别区域对采集的仪表图像进行轮廓检测获得第一仪表盘轮廓图，使用预先设置的面积分位比对所述第一仪表盘轮廓图进行滤波并输出包括多个子轮廓的第二仪表盘轮廓图，并获取各子轮廓的质心；
S4：根据预先设置的轮廓信息和各子轮廓的质心获取所述第二仪表盘轮廓图的圆心和半径，并以所述圆心为坐标原点建立直角坐标系，所述直角坐标系包括四个象限；
S6：对所述仪表图像进行霍夫直线检测获取至少一条第一指针线段，根据预先设置的指针信息对所述至少一条第一指针线段进行指针清洗并获取第二指针线段，根据所述第二指针线段相对于所述直角坐标系的斜率、以及位于所述直角坐标系的象限获取所述第二指针线段的位置信息。
在本发明的一个实施例中，根据仪表盘上各子轮廓具有均匀相似性的特性对仪表盘进行轮廓检测以获取仪表盘轮廓、圆心和半径，再通过霍夫直线检测识别仪表盘的指针，并基于仪表盘轮廓的圆心建立直角坐标系，根据指针相对于直角坐标系的斜率和象限位置信息获取指针信息，能够识别各种仪表盘是否出现，特别是没有闭合曲线的仪表盘，在提高仪表盘识别的准确性的同时，进一步提高仪表盘识别的泛化性。
在一个实施例中，如图2所示为本发明实施例采集的车内速度仪表的仪表图像，该仪表图像包括有非闭合圆的仪表盘轮廓1、指针2和具体显示数值3。
在本发明的一个实施例中，所述仪表图像为对显示屏显示的内容实时拍摄的图像，可以为车辆生产阶段的测试图像、也可以为车辆行驶时的实际显示图像，本发明对此不做具体限定。具体识别过程如下：
首先，对仪表图像进行轮廓识别。
在本发明的一个实施例中，根据预先设置的识别区域，即指定的ROI区域(Region of Interest，感兴趣区域)，例如，对图2所示的仪表盘所在区域4进行轮廓检测，具体的，仪表盘包括多个子轮廓，例如标识阶段刻度的第一子轮廓101和标识基本刻度的第二子轮廓102，根据各子轮 廓具有均匀相似性的特性，利用边缘检测对仪表图像的ROI区域进行轮廓检测。
根据轮廓检测获得如图3所示的图像二值化后的第一仪表盘轮廓图，包括检测的第一子轮廓101和第二子轮廓103。在本发明的一个实施例中，通过OpenCV标定的平面直角坐标系进行轮廓标识，具体的，根据零阶距获取每个子轮廓的面积，根据一阶距获取每个子轮廓的重心坐标，即质心。再依据仪表盘刻度线轮廓均匀的特点，针对面积不为0的轮廓进行分位点提取。在本发明的一个实施例中，依据单变量轮廓面积进行数据清洗，根据仪表盘的各子轮廓具有均匀相似性的特点，提取1/4到3/4分位点的轮廓获得第二仪表盘轮廓图。
在一个可选的实施例中，该仪表盘识别方法还包括在对仪表图像进行轮廓识别前设置所述仪表盘的识别区域。
在本发明的一个实施例中，根据待测仪表盘的先验信息，设置识别区域以便于对仪表图像进行识别，提高所述仪表盘识别的准确性，降低仪表盘识别时间。
其次，获取第二仪表盘轮廓图的圆心和半径。
在本发明的一个实施例中，根据各子轮廓的质心获取各子轮廓的左边界和右边界，同时再根据预先设置的仪表盘的上下左右边界范围，根据各子轮廓的左边界和右边界获取所述第二仪表轮廓图的左边界和右边界获取所述第二仪表盘轮廓图的圆心，再根据所述第二仪表盘轮廓图的圆心、左边界和/或右边界获取第二仪表盘轮廓图的半径。
具体的，如图3所示，根据各子轮廓的左边界和右边界获取第二仪表轮廓图的左边界子轮廓和右边界子轮廓，根据OpenCV标定的平面直角坐标系，左边界子轮廓的坐标为(x1，y1)，右边界子轮廓的坐标为(x2，y2)，从而获得第二仪表盘轮廓图的圆心(x0，y0)；具体的：x0＝(x1+x2)/2，y0＝(y1+y2)/2。根据第二仪表盘轮廓图的圆心和左边界子轮廓获取半径，或者根据第二仪表盘轮廓图的圆心和右边界子轮廓获取半径，或者根据第二仪表盘轮廓图的圆心、左边界子轮廓和右边界子轮廓获取半径R。
为便于后续识别仪表盘的指针，在本发明的一个实施例中，如图4所示，以第二仪表盘轮廓图的圆心为坐标原点(0，0)建立直角坐标系， 包括x轴和y轴，所述直角坐标系包括四个象限，分别为第一象限10，第二象限20，第三象限30和第四象限40。
为了进一步提高识别准确性，在一个可选的实施例中，如图5所示，该仪表盘识别方法还包括：
S5：根据各子轮廓的质心获取所述第二仪表轮廓图的上边界，并根据所述第二仪表轮廓图的上边界和圆心验证所述半径。
在本发明的一个实施例中，如图3所示，该仪表盘识别方法还包括所述第二仪表轮廓图的上边界子轮廓的坐标(x3，y3)，使用上边界子轮廓和圆心的距离对前述获得的半径R进行回归检验。
在一个可选的实施例中，该仪表盘识别方法还包括在获取第二仪表盘轮廓图的圆心和半径前设置所述仪表盘的轮廓信息。
在本发明的一个实施例中，根据待测仪表盘的先验信息，设置轮廓信息以便于对仪表图像进行识别，具体的，所述轮廓信息包括仪表盘的上下左右边界范围，能够提高所述仪表盘识别的准确性，降低仪表盘识别时间。
最后，使用霍夫直线检测方法检测仪表盘的指针。
在本发明的一个实施例中，使用霍夫直线检测方法对仪表图像进行直线检测，获得多条第一指针线段，根据预先设置的指针信息对各第一指针线段进行过滤，例如，根据预先设置的圆心到指针的距离阈值对各第一指针线段进行判断，当圆心到第一指针线段的距离大于距离阈值则过滤该第一指针线段；再根据预先设置的指针长度与圆心的位置关系对各第一指针线段进行判断，例如判断第一指针线段的一端是否在仪表盘的轮廓内、并且另一端是否在仪表盘的轮廓外，若满足则表明该第一指针线段为仪表的指针，否则将该第一指针线段进行过滤；从而获得仪表图像的指针，即第二指针线段。
根据第二指针线段相对于基于圆心的直角坐标系的斜率和该第二指针线段所处的象限位置获取指针的位置信息。如图4所示，第二指针线段2在直角坐标系的第三象限30，根据第二指针线段相对于直角坐标系的斜率，能够获得第二指针线段在仪表盘中指向的角度位置，例如该第二指针线段相对于仪表的零刻度线210指向30度的位置。
在一个可选的实施例中，该仪表盘识别方法还包括在使用霍夫直线 检测方法检测仪表盘的指针前设置所述仪表盘的指针信息。
在本发明的一个实施例中，根据待测仪表盘的先验信息，设置指针信息以便于对仪表图像进行识别，具体的，所述指针信息包括圆心到指针的距离阈值、以及指针长度与圆心的位置关系，能够提高所述仪表盘识别的准确性，降低仪表盘识别时间。
在一个可选的实施例中，根据预先设置的仪表盘映射表和所述位置信息获取所述仪表图像中仪表盘的指针读数。
在本发明的一个实施例中，该仪表盘识别方法还可以包括预先设置的仪表映射表。该仪表映射表包括仪表盘的刻度和角度位置对应关系，根据该仪表映射表和位置信息能够获取第二指针线段的具体读数。
如图4所示，在本发明的一个实施例中，仪表盘为对称仪表盘，指针读数与角度的关系为：
其中，N为指针的读数，M为所述仪表盘的量程，α为指针与零刻度线210间的夹角，θ为仪表盘的零刻度线210与y轴的夹角、也为仪表盘的满刻度线220与y轴的夹角，则2θ为仪表盘的零刻度线210与满刻度线220之间的夹角，360°－2θ为指针在满量程时对应的角度。
在另一个实施例中，当所述仪表盘为如图6所示的非对称仪表盘时，指针读线与角度间的关系为：
其中，零刻度线的初始角度为α,指针在满量程时对应的角度为β。N为所述指针的读数，M为所述汽车仪表的量程，θ为所述指针的当前位置与零刻度线间夹角，β－α为所述汽车仪表的零刻度线与满刻度线之间的夹角，360°－2θ为指针在满量程时对应的角度。
基于上述识别的仪表盘，为进一步检测仪表盘，如图5所示，在一个可选的实施例中，该仪表盘识别方法还包括：
S7：对所述仪表图像进行光学字符识别获取所述仪表盘的显示数据，判断所述显示数据与所述指针读数是否一致并输出判断结果。
在本发明的一个实施例中，如图2所示，进一步使用光学字符识别方法识别所述仪表图像中的显示数据3，即显示屏显示的车辆速度，例如车辆时速为60km/h时，根据识别的指针读出的速度与显示屏显示的车辆速度进行比对，若两者一致则进一步验证对所示仪表图像的识别准确度。
需要说明的是，本发明实施例还包括根据从车辆CAN接口读出的车辆速度，并以该车辆速度对识别的指针读出的速度进行校验、以及对光学字符识别出的显示速度进行校验，在此不再赘述。
至此，完成对如图2所示的仪表图像的仪表盘是否出现的识别，根据仪表盘上各子轮廓具有均匀相似性的特性对仪表盘进行轮廓检测以获取仪表盘轮廓、圆心和半径，再通过霍夫直线检测识别仪表盘的指针，并基于仪表盘轮廓的圆心建立直角坐标系，根据指针相对于直角坐标系的斜率和象限位置信息获取指针信息，能够识别各种仪表盘，特别是没有闭合曲线的仪表盘，在提高仪表盘识别的准确性的同时，进一步提高仪表盘识别的泛化性。
需要说明的是，本发明实施例以车辆上显示仪表信息的显示屏为例进行说明，仅为说明本发明的仪表盘识别方法，并未限定该仪表盘识别方法仅应用于车辆显示屏的仪表盘检测，该仪表盘识别方法能够应用于对各种仪表盘的检测和识别，具有广泛地应用前景。
本发明的第二实施例还提供一种仪表盘识别装置，如图7所示，包括：图像采集装置、图像处理装置和控制器，其中，所述控制器配置为：
通过所述图像采集装置对显示屏进行图像采集并获取仪表图像；
通过所述图像处理装置根据预先设置的识别区域对所述仪表图像进行轮廓检测获得第一仪表盘轮廓图，使用预先设置的面积分位比对所述第一仪表盘轮廓图进行滤波并输出包括多个子轮廓的第二仪表盘轮廓图，并获取各子轮廓的质心；
根据预先设置的轮廓信息和各子轮廓的质心获取所述第二仪表盘轮廓图的圆心和半径，并以所述圆心为坐标原点建立直角坐标系，所述直角坐标系包括四个象限；
通过所述图像处理装置对所述仪表图像进行霍夫直线检测获取至少一条第一指针线段，根据预先设置的指针信息对所述至少一条第一指针线段进行指针清洗并获取第二指针线段，根据所述第二指针线段相对于 所述直角坐标系的斜率、以及位于所述直角坐标系的象限获取所述第二指针线段的位置信息。
在本发明的一个实施例中，仪表盘识别装置利用图像采集装置采集待测仪表盘的仪表图像，所述图像采集装置为摄像头，响应于控制器的指令采集仪表图像并传输至控制器。图像处理装置用于对仪表图像进行数据处理和识别，具体的，包括对仪表图像进行轮廓识别，并根据仪表盘的上各刻度的子轮廓具有均匀相似性的特性进行检测并获取仪表盘的轮廓；然后控制器根据仪表盘的轮廓确定仪表盘的圆心和半径，并基于仪表盘的圆心建立直角坐标系以便于识别仪表盘的指针位置；最后，图像处理装置对仪表图像进行霍夫直线检测、对检测到的线段进行过滤，例如通过圆心到指针的距离阈值、以及通过指针长度与圆心的位置关系过滤不符合条件的线段，从而确定指针，并根据指针所处象限和相对于直角坐标系的斜率进一步获取指针的位置。具体实施方式参见前述实施例，在此不再赘述。
在一个可选的实施例中，所述控制器进一步配置为：
根据预先设置的仪表盘映射表和所述位置信息获取所述仪表图像中仪表盘的指针读数；
对所述仪表图像进行光学字符识别获取所述仪表盘的显示数据，判断所述显示数据与所述指针读数是否一致并输出判断结果。
在本发明的一个实施例中，进一步通过仪表盘映射表，根据指针的位置获取指针读数，从而完成仪表盘的读数识别。同时，通过使用光学字符识别方法识别仪表盘的显示数据，并根据识别的指针读出的数据与显示屏显示的数据进行比对，若两者一致则进一步验证了对仪表图像的识别准确度。
在一个可选的实施例中，所述仪表盘识别装置还包括用于切换所述显示屏显示内容的页面切换装置，所述控制器进一步配置为：通过所述页面切换装置切换所述显示屏的显示内容。
在本发明的一个实施例中，通过能够触发显示屏显示内容切换的页面切换装置对显示屏的显示内容进行切换，例如将显示屏的显示内容从文字信息、图像信息或视频信息切换为仪表盘显示，从而便于仪表盘识别装置对显示屏上显示的仪表盘进行采集、并对采集的图像进行识别。
需要说明的是，当显示屏的显示内容不是仪表盘时，仪表盘识别装置对显示内容进行采集和识别，当无法识别出仪表盘轮廓时判断显示内容不是仪表盘，退出识别，等待再次接收到采集的图像时再次识别，或者发出提示信息。例如，有些应用场景下，仪表盘不应该显示，在此情况下无法识别出仪表盘轮廓时，就退出识别；如果识别出仪表盘轮廓时，则发出提示信息。
并且，本发明对页面切换装置不作具体限定，可以为通过有线或无线网络与显示屏连接的切换装置，可以为通过车辆自身的CAN接口连接的切换装置，以能够实现对显示屏的显示内容进行切换为设计准则，在此不再赘述。
在一个可选的实施例中，所述仪表盘识别装置还包括用于记录识别信息的日志单元，所述控制器进一步配置为：通过所述日志单元记录所述判断结果。
在本发明的一个实施例中，通过日志单元记录对仪表图像识别的结果，例如记录前述实施例中的显示数据、以及指针读出数据的比对结果。需要说明的是，本发明对日志单元不作具体限定，可以记录仪表识别装置对显示屏的识别结果，也可以通过连接车辆的日志接口获取车辆的运行记录，例如获取车辆传感器的感测数据等，在此不再赘述。
本发明的第三实施例提供一种计算机可读存储介质，其中存储有计算机程序，所述计算机程序被处理器执行时实现：S2：根据预先设置的识别区域对采集的仪表图像进行轮廓检测获得第一仪表盘轮廓图，使用预先设置的面积分位比对所述第一仪表盘轮廓图进行滤波并输出包括多个子轮廓的第二仪表盘轮廓图，并获取各子轮廓的质心；S4：根据预先设置的轮廓信息和各子轮廓的质心获取所述第二仪表盘轮廓图的圆心和半径，并以所述圆心为坐标原点建立直角坐标系，所述直角坐标系包括四个象限；S6：对所述仪表图像进行霍夫直线检测获取至少一条第一指针线段，根据预先设置的指针信息对所述至少一条第一指针线段进行指针清洗并获取第二指针线段，根据所述第二指针线段相对于所述直角坐标系的斜率、以及位于所述直角坐标系的象限获取所述第二指针线段的位置信息。
在实际应用中，所述计算机可读存储介质可以采用一个或多个计算 机可读的介质的任意组合。计算机可读介质可以是计算机可读信号介质或者计算机可读存储介质。计算机可读存储介质例如可以是但不限于电、磁、光、电磁、红外线、或半导体的系统、装置或器件，或者任意以上的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：具有一个或多个导线的电连接、便携式计算机磁盘、硬盘、随机存取存储器(RAM)、只读存储器(ROM)、可擦式可编程只读存储器(EPROM或闪存)、光纤、便携式紧凑磁盘只读存储器(CD-ROM)、光存储器件、磁存储器件、或者上述的任意合适的组合。在本发明的一个实施例中，计算机可读存储介质可以是任何包含或存储程序的有形介质，所述计算机程序可以被指令执行系统、装置或者器件使用或者与其结合使用。
计算机可读的信号介质可以包括在基带中或者作为载波一部分传播的数据信号，其中承载了计算机可读的程序代码。这种传播的数据信号可以采用多种形式，包括但不限于电磁信号、光信号或上述的任意合适的组合。计算机可读的信号介质还可以是计算机可读存储介质以外的任何计算机可读介质，该计算机可读介质可以发送、传播或者传输用于由指令执行系统、装置或者器件使用或者与其结合使用的程序。
计算机可读介质上包含的程序代码可以用任何适当的介质传输，包括但不限于无线、电线、光缆、RF等等，或者上述的任意合适的组合。
可以以一种或多种程序设计语言或其组合来编写用于执行本发明操作的计算机程序代码，所述计算机程序设计语言包括面向对象的程序设计语言—诸如Java、Smalltalk、C++，还包括常规的过程式程序设计语言—诸如“C”语言或类似的程序设计语言。程序代码可以完全地在用户计算机上执行、部分地在用户计算机上执行、作为一个独立的软件包执行、部分在用户计算机上部分在远程计算机上执行、或者完全在远程计算机或服务器上执行。在涉及远程计算机的情形中，远程计算机可以通过任意种类的网络—包括局域网(LAN)或广域网(WAN)—连接到用户计算机，或者，可以连接到外部计算机(例如利用因特网服务提供商来通过因特网连接)。
如图8所示，本发明的第四实施例提供一种计算机设备12。该计算机设备12以通用计算设备的形式表现，其中的组件可以包括但不限于：一个或者多个处理器或者处理单元16，系统存储器28，连接不同系统组 件(包括系统存储器28和处理单元16)的总线18。
总线18表示几类总线结构中的一种或多种，包括存储器总线或者存储器控制器，外围总线，图形加速端口，处理器或者使用多种总线结构中的任意总线结构的局域总线。举例来说，这些体系结构包括但不限于工业标准体系结构(ISA)总线，微通道体系结构(MAC)总线，增强型ISA总线、视频电子标准协会(VESA)局域总线以及外围组件互连(PCI)总线。
计算机设备12典型地包括多种计算机系统可读介质。这些介质可以是任何能够被计算机设备12访问的可用介质，包括易失性和非易失性介质，可移动的和不可移动的介质。
系统存储器28可以包括易失性存储器形式的计算机系统可读介质，例如随机存取存储器(RAM)30和/或高速缓存存储器32。计算机设备12可以进一步包括其它可移动/不可移动的、易失性/非易失性计算机系统存储介质。仅作为举例，存储系统34可以用于读写不可移动的、非易失性磁介质(图8未显示，通常称为“硬盘驱动器”)。尽管图8中未示出，可以提供用于对可移动非易失性磁盘(例如“软盘”)读写的磁盘驱动器，以及对可移动非易失性光盘(例如CD-ROM，DVD-ROM或者其它光介质)读写的光盘驱动器。在这些情况下，每个驱动器可以通过一个或者多个数据介质接口与总线18相连。存储器28可以包括至少一个程序产品，该程序产品具有一组(例如至少一个)程序模块，这些程序模块被配置以执行本发明各实施例的功能。
具有一组(至少一个)程序模块42的程序/实用工具40，可以存储在例如存储器28中，这样的程序模块42包括但不限于操作系统、一个或者多个应用程序、其它程序模块以及程序数据，这些实施例中的每一个或某种组合中可能包括网络环境的实现。程序模块42通常执行本发明所描述的实施例中的功能和/或方法。
计算机设备12也可以与一个或多个外部设备14(例如键盘、指向设备、显示器24等)通信，还可与一个或者多个使得用户能与该计算机设备12交互的设备通信，和/或与使得该计算机设备12能与一个或多个其它计算设备进行通信的任何设备(例如网卡，调制解调器等等)通信。这种通信可以通过输入/输出(I/O)接口22进行。并且，计算机设备12 还可以通过网络适配器20与一个或者多个网络(例如局域网(LAN)，广域网(WAN)和/或公共网络，例如因特网)通信。如图8所示，网络适配器20通过总线18与计算机设备12的其它模块通信。应当明白，尽管图8中未示出，可以结合计算机设备12使用其它硬件和/或软件模块，包括但不限于：微代码、设备驱动器、冗余处理单元、外部磁盘驱动阵列、RAID系统、磁带驱动器以及数据备份存储系统等。
处理器单元16通过运行存储在系统存储器28中的程序，从而执行各种功能应用以及数据处理，例如实现本发明实施例所提供的一种仪表盘识别方法。
可以理解，图8显示的计算机设备12仅仅是一个实施例，不应对本发明实施例的功能和使用范围带来任何限制。
与现有技术相比较，本发明根据仪表盘上各子轮廓具有均匀相似性的特性对仪表盘进行轮廓检测以获取仪表盘轮廓、圆心和半径，再通过霍夫直线检测识别仪表盘的指针，并基于仪表盘轮廓的圆心建立直角坐标系，根据指针相对于直角坐标系的斜率和象限位置信息获取指针信息，能够识别各种仪表盘信息，特别是没有闭合曲线的仪表盘，在提高仪表盘识别的准确性的同时，进一步提高仪表盘识别的泛化性。而且，利用本发明能够辨别仪表盘是否出现，以避免仪表盘错误显示。
上面对本发明所提供的仪表盘识别方法、识别装置、存储介质和计算机设备进行了详细的说明。对本领域的一般技术人员而言，在不背离本发明实质内容的前提下对它所做的任何显而易见的改动，都将构成对本发明专利权的侵犯，将承担相应的法律责任。

Claims (10)

  1. 一种仪表盘识别方法，其特征在于包括如下步骤：
    S2：根据预先设置的识别区域对采集的仪表图像进行轮廓检测获得第一仪表盘轮廓图，使用预先设置的面积分位比对所述第一仪表盘轮廓图进行滤波并输出包括多个子轮廓的第二仪表盘轮廓图，并获取各子轮廓的质心；
    S4：根据预先设置的轮廓信息和各子轮廓的质心获取所述第二仪表盘轮廓图的圆心和半径，并以所述圆心为坐标原点建立直角坐标系，所述直角坐标系包括四个象限；
    S6：对所述仪表图像进行霍夫直线检测获取至少一条第一指针线段，根据预先设置的指针信息对所述至少一条第一指针线段进行指针清洗并获取第二指针线段，根据所述第二指针线段相对于所述直角坐标系的斜率、以及位于所述直角坐标系的象限获取所述第二指针线段的位置信息。
  2. 如权利要求1所述的仪表盘识别方法，其特征在于，在S4之后、S6之前，所述仪表盘识别方法还包括：
    S5：根据各子轮廓的质心获取所述第二仪表轮廓图的上边界，并根据所述第二仪表轮廓图的上边界和圆心验证所述半径。
  3. 如权利要求1所述的仪表盘识别方法，其特征在于，S6进一步包括：
    根据预先设置的仪表盘映射表和所述位置信息获取所述仪表图像中仪表盘的指针读数。
  4. 如权利要求3所述的仪表盘识别方法，其特征在于在S6之后，所述仪表盘识别方法还包括：
    S7：对所述仪表图像进行光学字符识别获取所述仪表盘的显示数据，判断所述显示数据与所述指针读数是否一致并输出判断结果。
  5. 如权利要求4所述的仪表盘识别方法，其特征在于在S2之前，所述仪表盘识别方法还包括：
    S1：根据所述仪表盘显示的先验信息设置所述仪表盘的识别区域、轮廓信息和指针信息。
  6. 一种仪表盘识别装置，其特征在于包括图像采集装置、图像处理 装置和控制器，其中，所述控制器配置为：
    通过所述图像采集装置对显示屏进行图像采集并获取仪表图像；
    通过所述图像处理装置根据预先设置的识别区域对所述仪表图像进行轮廓检测获得第一仪表盘轮廓图，使用预先设置的面积分位比对所述第一仪表盘轮廓图进行滤波并输出包括多个子轮廓的第二仪表盘轮廓图，并获取各子轮廓的质心；
    根据预先设置的轮廓信息和各子轮廓的质心获取所述第二仪表盘轮廓图的圆心和半径，并以所述圆心为坐标原点建立直角坐标系，所述直角坐标系包括四个象限；
    通过所述图像处理装置对所述仪表图像进行霍夫直线检测获取至少一条第一指针线段，根据预先设置的指针信息对所述至少一条第一指针线段进行指针清洗并获取第二指针线段，根据所述第二指针线段相对于所述直角坐标系的斜率、以及位于所述直角坐标系的象限获取所述第二指针线段的位置信息。
  7. 如权利要求6所述的仪表盘识别装置，其特征在于，所述控制器进一步配置为：
    根据预先设置的仪表盘映射表和所述位置信息获取所述仪表图像中仪表盘的指针读数；
    对所述仪表图像进行光学字符识别获取所述仪表盘的显示数据，判断所述显示数据与所述指针读数是否一致并输出判断结果。
  8. 如权利要求7所述的仪表盘识别装置，其特征在于还包括用于切换所述显示屏显示内容的页面切换装置，所述控制器进一步配置为：通过所述页面切换装置切换所述显示屏的显示内容；和/或，
    还包括用于记录识别信息的日志单元，所述控制器进一步配置为：通过所述日志单元记录所述判断结果。
  9. 一种计算机可读存储介质，其上存储有计算机程序，其特征在于：所述计算机程序被处理器执行时实现如权利要求1～5中任意一项所述的仪表盘识别方法。
  10. 一种计算机设备，包括存储器、处理器及存储在存储器上并可在处理器上运行的计算机程序，其特征在于：所述处理器执行所述计算机程序时实现如权利要求1～5中任意一项所述的仪表盘识别方法。
PCT/CN2023/091733 2022-04-30 2023-04-28 一种仪表盘识别方法、识别装置、存储介质和计算机设备 WO2023208214A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210476855.6A CN117011833A (zh) 2022-04-30 2022-04-30 一种仪表盘识别方法、识别装置、存储介质和计算机设备
CN202210476855.6 2022-04-30

Publications (1)

Publication Number Publication Date
WO2023208214A1 true WO2023208214A1 (zh) 2023-11-02

Family

ID=88517955

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/091733 WO2023208214A1 (zh) 2022-04-30 2023-04-28 一种仪表盘识别方法、识别装置、存储介质和计算机设备

Country Status (2)

Country Link
CN (1) CN117011833A (zh)
WO (1) WO2023208214A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117274966A (zh) * 2023-11-23 2023-12-22 江西小马机器人有限公司 室外工业仪表监测方法、系统、可读存储介质及计算机

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106295658A (zh) * 2016-08-13 2017-01-04 国网福建省电力有限公司 一种变电站指针式仪表读数自动识别系统
CN107038447A (zh) * 2017-04-26 2017-08-11 大连理工大学 一种基于机器视觉的指针式仪表识别方法
CN110084251A (zh) * 2019-04-29 2019-08-02 北京史河科技有限公司 一种仪表识别方法、装置及存储介质
US20210142099A1 (en) * 2019-11-07 2021-05-13 Sap Se Pointer recognition for analog instrument image analysis

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN106295658A (zh) * 2016-08-13 2017-01-04 国网福建省电力有限公司 一种变电站指针式仪表读数自动识别系统
CN107038447A (zh) * 2017-04-26 2017-08-11 大连理工大学 一种基于机器视觉的指针式仪表识别方法
CN110084251A (zh) * 2019-04-29 2019-08-02 北京史河科技有限公司 一种仪表识别方法、装置及存储介质
US20210142099A1 (en) * 2019-11-07 2021-05-13 Sap Se Pointer recognition for analog instrument image analysis

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
LIANG-HE SU, YE KAI-MING;TANG JIN-CHENG;LI MENG-FENG;WU GUO-LAN: "Research on Identification Techology of Circuit Breaker Pressure Gage Based on Image Processing", ELECTRIC SWITCHGEAR, vol. 2017, no. 6, 15 December 2017 (2017-12-15), pages 31 - 33, 38, XP093104754 *
SHU CHEN, WANG LEI: "Method for Testing of Pointer Instrument Based on Machine Vision", COMPUTER & DIGITAL ENGINEERING, vol. 44, no. 9, 20 September 2016 (2016-09-20), pages 1821 - 1826, XP093104752 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN117274966A (zh) * 2023-11-23 2023-12-22 江西小马机器人有限公司 室外工业仪表监测方法、系统、可读存储介质及计算机
CN117274966B (zh) * 2023-11-23 2024-04-19 江西小马机器人有限公司 室外工业仪表监测方法、系统、可读存储介质及计算机

Also Published As

Publication number Publication date
CN117011833A (zh) 2023-11-07

Similar Documents

Publication Publication Date Title
US11403757B2 (en) Sight line detection method and sight line detection device
EP3712805A1 (en) Gesture recognition method, device, electronic device, and storage medium
CN110378966B (zh) 车路协同相机外参标定方法、装置、设备及存储介质
WO2019196205A1 (zh) 外语教学评价信息生成方法以及装置
WO2023208214A1 (zh) 一种仪表盘识别方法、识别装置、存储介质和计算机设备
WO2020199694A1 (zh) 一种脊柱Cobb角测量方法、装置、可读存储介质及终端设备
CN110222703B (zh) 图像轮廓识别方法、装置、设备和介质
CN108156452B (zh) 一种检测传感器的方法、装置、设备及存储介质
WO2014090090A1 (zh) 角度测量方法和装置
CN112215060B (zh) 一种基于霍夫变换的高精度机械式仪表示数识别方法
CN111428374A (zh) 零件缺陷检测方法、装置、设备及存储介质
CN111027506B (zh) 视线方向的确定方法、装置、电子设备及存储介质
CN110796108B (zh) 一种人脸质量检测的方法、装置、设备及存储介质
CN112634235A (zh) 产品图像的边界检测方法和电子设备
CN111126268A (zh) 关键点检测模型训练方法、装置、电子设备及存储介质
CN111723799B (zh) 坐标定位方法、装置、设备及存储介质
WO2020134674A1 (zh) 掌纹识别方法、装置、计算机设备和存储介质
CN111985417A (zh) 功能部件识别方法、装置、设备及存储介质
CN111812545A (zh) 线路缺陷检测方法、装置、设备及介质
CN109141457B (zh) 导航评估方法、装置、计算机设备和存储介质
CN114821034A (zh) 目标检测模型的训练方法、装置、电子设备及介质
CN113963158A (zh) 一种掌静脉图像感兴趣区域提取方法及装置
CN112559340A (zh) 一种画面测试方法、装置、设备及存储介质
CN111124862B (zh) 智能设备性能测试方法、装置及智能设备
CN112966671A (zh) 一种合同检测方法、装置、电子设备及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 23795646

Country of ref document: EP

Kind code of ref document: A1