Dimension measurement method and system for supporting plate type aviation connecting piece

Abstract

The invention provides a dimension measurement method and system for a support plate type aviation connecting piece, and belongs to the technical field of part identification and detection. The method comprises the following steps: acquiring a complete space position picture set of the aviation connecting piece by adopting a light source time-sharing control system oriented to same position difference imaging; acquiring fillet characteristics of the aviation connecting piece; removing different plane images and measuring the plane size of the connecting piece base; obtaining a different-plane feature image, and carrying out size measurement on a different-plane feature region; according to the invention, the visual detection of the imaging plane of the camera is not interfered by different plane imaging, the accurate positioning of the support plate type aviation connecting piece can be realized, and the regional size measurement of a multi-angle plane image can be completed.

Description

Technical Field

[0001] The invention belongs to the technical field of parts identification and detection, and in particular relates to a dimension measurement method and system for a support plate type aviation connector. Background Art

[0002] The quality of aviation connectors is directly related to the performance of aircraft and the safety of passengers, so the accuracy of the dimensional measurement of aviation connectors needs to be guaranteed. At present, most factories still use workers to measure manually, which is costly and time-consuming. Using machine vision methods to measure part dimensions can improve efficiency and reduce costs. However, in the process of two-dimensional plane detection of parts, some three-dimensional features of the parts often lead to complex images, which greatly affects image analysis and subsequent dimensional measurement. Therefore, in order to ensure the dimensional measurement accuracy of aviation connectors, it is particularly important to remove the interference of different planes on the imaging plane.

[0003] However, due to the complex shape of the support plate type aviation connector, which is a spatial non-planar part, the removal of the different plane imaging requires the precise acquisition of the characteristics of the connector. The generalized image descriptor cannot characterize the position information of the connector. Moreover, the visual measurement of a single perspective cannot obtain the full size of the spatial connector. Therefore, a stable, multi-angle, high-precision position description method that can characterize the position of non-planar parts is needed to achieve accurate positioning of the support plate type aviation connector and meet the needs of high-precision measurement. Most existing technologies can only achieve the size measurement of planar parts based on two-dimensional images.

[0004] Therefore, it is necessary to design a high-precision dimensional measurement system for support plate type aviation connectors. Summary of the invention

[0005] In order to solve the technical problem that the existing technology cannot achieve accurate positioning of support plate type aviation connectors and meet the needs of high-precision measurement, the present invention provides a dimension measurement method and system for support plate type aviation connectors, which can ensure that the visual detection of the camera imaging plane is not interfered by the imaging of different planes, can achieve accurate positioning of support plate type aviation connectors, and complete the regional dimension measurement of multi-angle plane images. The technical solution is as follows:

[0006] In a first aspect, a method for measuring the dimensions of a support plate-type aviation connector is provided, the method comprising:

[0007] Step 1: Use a light source time-sharing control system for imaging differences at the same position to obtain a complete set of spatial position images of aviation connectors;

[0008] Step 2: Obtain fillet features of aviation connectors;

[0009] Step 3, remove the out-of-plane images and measure the plane dimensions of the connector base;

[0010] Step 4: Obtain the out-of-plane feature image and measure the size of the out-of-plane feature area.

[0011] Optionally, the process of building a light source time-sharing control system and obtaining difference images of the aviation connector under different lighting environments at the same position includes:

[0012] Step 1.1) Build a backlight illumination system: Place main light sources under and on the side of the aviation connector as the backlight source for the top-view camera and the side-view camera, respectively. Both use parallel backlights to ensure a stable and clear image of the connector outline.

[0013] Step 1.2) Build a vertical lighting system: Install a set of strip light sources on both sides of the top-view camera and the side-view camera, and use an angle ruler to calibrate the direction of each light source to ensure that the light hits the surface of the aviation connector vertically. Since the support plate plane and the base plane of the aviation connector are transitioned with rounded corners, a square shadow effect will appear in this part, which can be used as a separation area for different planes;

[0014] Step 1.3) Automatically switch the backlight source and the strip light source through time-sharing control technology to obtain difference images of the aviation connector under different lighting environments at the same position.

[0015] Optionally, it is characterized in that step 1.3) specifically includes:

[0016] Step 1.3.1) In the initial state, the MCU controls the backlight source to switch from the off state to the on state, and the strip light source is in the off state; after the camera takes a photo, a first signal indicating that the photo acquisition is completed is sent to the PC, wherein the camera is a top-view camera and a side-view camera;

[0017] Step 1.3.2) After the PC receives the first signal sent by the camera indicating that the photo collection is complete, the PC sends a first control signal to the MCU. The MCU controls the backlight source to turn off and the strip light source to turn on. After the camera takes a photo again, the PC sends a second signal indicating that the photo collection is complete.

[0018] Step 1.3.3) After the PC receives the second signal sent by the camera to indicate that the photo acquisition is completed, it sends a second control signal to the MCU, and the MCU controls the strip light source to turn off, completing a photo cycle; through a photo cycle, the backlight illumination image and the vertical illumination image of the same position in a single direction can be obtained. The overhead camera and the side view camera respectively perform the above-mentioned photo cycle operations to obtain a complete set of spatial position images of aviation connectors.

[0019] Further, after step 1.3), the method further includes:

[0020] Step 1.4) Adjust the imaging area of ​​the top-view camera and the side-view camera so that when the strip light source is turned on, the imaging area of ​​the camera does not include the reflected light from the surface of the backlight source to avoid affecting the camera imaging; calibrate the camera to determine the size value of the unit pixel in the shooting environment.

[0021] Optionally, step 2 specifically includes:

[0022] Step 2.1) The PC uses a threshold segmentation algorithm to obtain a square shadow area image based on the overhead image of the aviation connector at the same position under different lighting environments obtained in step 1, counts the number of square shadow areas detected, and automatically adjusts the position of the aviation connector according to the number of square shadow areas detected;

[0023] Step 2.2) If there is only one square shadow area detected, adjust the number of rounded corners at the position of the aviation connector: the PC obtains an edge straight line by fitting the long side of the rectangular enclosing frame of the square shadow area, calculates a unit direction vector perpendicular to the straight line, and points to the square shadow area. According to the unit direction vector, the MCU is instructed to drive the electric loading platform to move; the center of the rectangular enclosing frame is moved to the center of the camera field of view to ensure that two rounded corner areas can be identified;

[0024] Step 2.3) If the number of detected square shadow areas is two, the position difference adjustment of the aviation connector position is performed: the vertical illumination video of the aviation connector is input through the camera's video stream mode, and the PC calculates the pixel areas of the two detected square shadow areas in real time. If the pixel area difference between the two square shadow areas is less than the set threshold, the position adjustment is stopped; otherwise, the edge straight line is obtained by fitting the long sides of the square shadow areas, and the unit direction vector perpendicular to the straight line is calculated and points to the direction of the larger shadow area. According to the unit direction vector, the MCU is instructed to drive the electric carrier to move.

[0025] Optionally, step 3 specifically includes:

[0026] Step 3.1) After the electric loading platform finishes position adjustment, the PC processes the two images acquired by the overhead camera under different lighting conditions at the same position to remove interference from different plane imaging:

[0027] Step 3.2) After eliminating the interference of different plane imaging, the plane image is processed in regions according to the connectivity relationship. For each sub-region, the PC detects the straight contour of the aviation connector, and the remaining contours are non-linear contours. The non-linear contours are curve fitted to achieve the extraction of the straight contour and curved contour of the edge of the aviation connector base;

[0028] Step 3.3) Based on the scale calibration results obtained in step 1.4), the PC calculates the length of the straight contour and the characteristic size of the curved contour, converts the pixel value into the actual size value, and then realizes the measurement of the external dimensions of the base of the aviation connector.

[0029] Optionally, step 3.1) specifically includes:

[0030] Step 3.1.1) The PC uses a threshold segmentation algorithm to process the vertical illumination image to obtain a square shadow area image;

[0031] Step 3.1.2) PC fits the longer side lines of the two square-shaped shadow areas to obtain a total of four parallel straight lines, and selects the two closest straight lines as the separation lines;

[0032] Step 3.1.3) The PC applies a dividing line to the backlit image, fills the middle part of the dividing line with a white background, and divides the backlit image into two parts, thereby achieving the purpose of removing interference from different plane imaging.

[0033] Optionally, step 4 specifically includes:

[0034] Step 4.1) PC segments the rounded corner area based on the rounded corner shadow image extracted from the top-view camera image, calculates the minimum enclosing rectangle of a single rounded corner area, calculates the angles α and β between its long and short sides and the positive direction of the X-axis, and calculates the area S of the shadow image corresponding to the rounded corner area, and constructs the rounded corner feature direction descriptor (α, β, S);

[0035] Step 4.2) The PC rotates the aviation connector clockwise by an angle of α and counterclockwise by an angle of (1-β) according to the rounded corner feature descriptor, so that the long side and the short side of the rectangle are aligned with the imaging plane of the side-view camera, and obtains the out-of-plane feature image through the side-view camera;

[0036] Step 4.3) During the rotation process of step 4.2), the PC calculates the additional displacement caused by the rotation and instructs the MCU to drive the electric loading platform to reset the position of the aviation connector to the position before the rotation. At the same time, the position of the aviation connector is fine-tuned according to the area S in the fillet feature descriptor to ensure that the area of ​​the fillet area remains unchanged;

[0037] Step 4.4) The PC determines the clarity of the image and fine-tunes the electric loading platform in a direction perpendicular to the side-view camera so that the side-view camera image is clear;

[0038] Step 4.5) After the characteristic surface of the aviation connector coincides with the imaging plane of the side view camera, the PC extracts the edge straight lines and curve contours of the support plate plane of the aviation connector according to step 3.2), thereby completing the measurement of the external dimensions of the support plate plane of the aviation connector.

[0039] In a second aspect, a dimension measurement system for a support plate type aviation connector is provided, using any method described in the first aspect, wherein the system comprises: a light source time-sharing control system, an MCU, a PC, and an electric loading platform.

[0040] MCU is connected to the light source time-sharing control system and PC, and the light source time-sharing control system is connected to PC.

[0041] The electric loading platform is arranged below the backlight source of the overhead camera and is connected to the MCU.

[0042] Optionally, the light source time-sharing control system includes: a top-view camera, a side-view camera, a backlight illumination system, and a vertical illumination system;

[0043] The backlight illumination system includes a backlight source for a top-view camera disposed below the aviation connector and a backlight source for a side-view camera disposed on the side of the aviation connector;

[0044] The vertical lighting system includes a group of strip light sources installed on both sides of the top-view camera and the side-view camera.

[0045] The beneficial effects of the dimension measurement method and system for support plate type aviation connectors provided by the present invention are at least:

[0046] (1) A light source time-sharing control system for differential imaging at the same position. The time-sharing control technology is used to realize the automatic switching between the main light source and the strip light source, which can ensure that images of parts under different lighting environments are obtained separately.

[0047] (2) Automatic position adjustment based on rounded corner area in visual inspection of aviation connectors can ensure that a sufficient number of rounded corner features of randomly placed aviation connectors can be accurately detected in camera imaging so as to delete out-of-plane information;

[0048] (3) The method of eliminating the non-planar imaging images to measure the dimensions of non-planar aviation connectors can realize the measurement of the base plane dimensions of non-planar aviation connectors. The proposed method of adjusting the connector posture can achieve its precise spatial positioning with the help of rounded corner features, thereby completing the measurement of the non-planar dimensions of the connectors. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 This is a schematic diagram of the light source time-sharing control system of the present invention;

[0050] Figure 2 It is a structural block diagram of the measurement system of the present invention;

[0051] Figure 3 This is a schematic diagram of the square shadow effect;

[0052] Figure 4 This is a schematic diagram of the extraction effect of the square shadow area;

[0053] Figure 5 Schematic diagram of removing the imaging effect of different planes;

[0054] Figure 6 Schematic diagram of the calculation effect of non-planar feature size. DETAILED DESCRIPTION

[0055] The present invention is further described in detail below through specific implementation modes and drawings.

[0056] like Figure 1 , Figure 2 As shown, an embodiment of the present invention provides a method for measuring the size of a support plate-type aviation connector, comprising the following steps:

[0057] Step 1: Use a light source time-sharing control system for imaging differences at the same position to obtain a complete set of spatial position images of aviation connectors.

[0058] In the embodiment of the present invention, under both the top view and the side view, the main light source adopts parallel backlight, so that a stable and clear connector outline image can be obtained; a group of strip light sources are respectively installed on both sides of the top view camera and the side view camera to build a vertical lighting system; the time-sharing control technology is used to realize the logical time-sharing switching of the backlight light source and the strip light source, so as to ensure that the difference images of the aviation connector under different lighting environments are obtained respectively; the imaging area of ​​the camera is adjusted to ensure that when the strip light source is on, the surface reflection of the backlight light source does not affect the imaging;

[0059] In one possible implementation, the process of building a light source time-sharing control system and obtaining difference images of aviation connectors in different lighting environments at the same position is as follows:

[0060] Step 1.1) Build a backlight illumination system, and place main light sources under and on the side of the aviation connector, respectively called the top-view camera backlight light source and the side-view camera backlight light source. Both use parallel backlights to ensure a stable and clear connector outline image;

[0061] Step 1.2) Build a vertical lighting system and install a set of strip light sources on both sides of the top-view camera and the side-view camera, such as Figure 1 As shown, strip light sources 1 and 2 are installed on both sides of the top-view camera, and strip light sources 3 and 4 are installed on both sides of the side-view camera. The direction of each light source is calibrated by an angle ruler to ensure that the light hits the surface of the aviation connector vertically. Since the support plate plane and the base plane of the aviation connector are transitioned by rounded corners, a square shadow effect will appear in this part, which can be used as a separation area for different planes, such as Figure 3 shown.

[0062] Step 1.3) Automatically switch the backlight source and the strip light source through time-sharing control technology to ensure that different images of the aviation connector under different lighting environments at the same position are obtained.

[0063] In one possible implementation, a single-chip microcomputer (MCU) and an industrial computer (PC) may be used for control, and the same logic is used in the top view direction and the side view direction, as follows:

[0064] Step 1.3.1) Initially, the MCU controls the backlight source to switch from the off state to the on state, and the strip light source is in the off state; after the camera takes a photo, it sends a first signal to the PC to indicate that the photo acquisition is completed;

[0065] Step 1.3.2) After receiving the first signal sent by the camera indicating that the photo collection is complete, the PC sends a first control signal to the MCU, so that the MCU controls the backlight source to turn off and the strip light source to turn on. After the camera takes a photo again, it sends a second signal to the PC indicating that the photo collection is complete;

[0066] Step 1.3.3) After receiving the second signal sent by the camera indicating that the photo acquisition is completed, the PC sends a second control signal to the MCU, so that the MCU controls the strip light source to turn off, completing a photo cycle;

[0067] Step 1.4) Adjust the imaging area of ​​the top-view camera and the side-view camera to ensure that when the strip light source is turned on, the imaging area of ​​the camera does not include the reflected light from the surface of the backlight source to avoid affecting the camera imaging; calibrate the camera to determine the size value of the unit pixel in the shooting environment;

[0068] Through one photographing cycle, a backlit image and a vertically illuminated image at the same position in a single direction can be obtained. The top-view camera and the side-view camera respectively perform the above-mentioned photographing cycle operations to obtain a complete set of spatial position images of the connector.

[0069] Step 2: Obtain the fillet features of aviation connectors.

[0070] Due to the existence of non-planar features, support plate-type aviation connectors need to include rounded corner transition areas. However, the rounded corner features of randomly placed aviation connectors often cannot be fully photographed. Therefore, an electric loading platform is used to carry aviation connectors, and the shadow area image of the rounded corners of randomly placed aviation connectors is obtained based on the threshold segmentation algorithm. The number of rounded corners and the position difference of the aviation connector position are adjusted according to the number of rounded corner area detections. After the number of rounded corners is adjusted, it can be ensured that two rounded corner areas are detected. After the position difference is adjusted, it can be ensured that the difference in pixel area of ​​the two detected rounded corner areas is less than the set threshold, thereby finally realizing the accurate acquisition of the rounded corner features of aviation connectors.

[0071] In one possible implementation, the process of obtaining the fillet feature of an aviation connector is as follows:

[0072] Step 2.1) Based on the aerial connector top view image obtained in step 1 under different lighting conditions at the same position, the PC uses a threshold segmentation algorithm to obtain the square shadow area image described in step 1.2). The processing result is as follows: Figure 4 As shown, the number of detected square shadow areas is counted, and shadow areas with very small areas are ignored. According to the number of detected square shadow areas, the adjustment strategies such as step 2.2) and step 2.3) are selected to automatically adjust the position of the aviation connector;

[0073] Step 2.2) If there is only one square shadow area detected, adjust the number of fillets at the position of the aviation connector. The PC obtains the edge straight line by fitting the long side of the rectangular bounding box of the square shadow area, calculates the unit direction vector perpendicular to the straight line, and points to the square shadow area. The MCU is instructed to drive the electric carrier to move according to the unit direction vector. Move the center of the rectangular bounding box to the center of the camera's field of view to ensure that the two fillets can be identified. During the rounded corner number adjustment stage, the single control movement time is slightly longer, so that the aviation connector can be adjusted to the approximate position as soon as possible to ensure that the two fillet areas are detected.

[0074] Step 2.3) If the number of detected square shadow areas is two, the position difference adjustment of the position of the aviation connector is performed. The vertical illumination video of the aviation connector is input through the video stream mode of the camera, and the PC calculates the pixel area of ​​the two detected square shadow areas in real time. If the pixel area difference of the two square shadow areas is less than the set threshold, the position adjustment is stopped. Otherwise, similar to step 2.2), the edge straight line is obtained by fitting the long side of the square shadow area, and the unit direction vector perpendicular to the straight line is calculated, and points to the direction of the larger shadow area. According to the unit direction vector, the MCU is instructed to drive the electric carrier to move. In the position difference adjustment stage, the single control movement time is short, which ensures that the position can be accurately adjusted.

[0075] In the adjustment of the number of fillets and the position difference of the aviation connector position, the corresponding formula for the movement of the electric loading platform can be expressed as:

[0076]

[0077] in, is the unit direction vector of the moving direction, is the displacement vector, step is the step length of the movement (which depends on the speed and movement time of the electric carrier platform), (x', y') is the coordinates of the electric carrier platform after movement, and (x, y) is the coordinates of the electric carrier platform before movement.

[0078] Step 3) Eliminate out-of-plane images and measure the plane dimensions of the connector base.

[0079] The image of the aviation connector after the position of the electric loading platform is adjusted is obtained by a bird's-eye view camera, and the rounded corner features are extracted through the difference image at the same position. The non-imaging plane image is removed to ensure that the size measurement of the base of the aviation connector is not disturbed. The least significant difference (LSD) algorithm is used to extract the straight lines in the contour of the aviation connector, and multiple curve fitting is performed on the non-straight contour to measure the outer dimensions of the connector base.

[0080] In one achievable manner, eliminating out-of-plane images and measuring the plane dimensions of the connector base may specifically include the following steps:

[0081] Step 3.1) After the electric loading platform has finished adjusting its position, Figure 5 As shown in the figure, the PC processes two images acquired by the overhead camera under different lighting conditions at the same position to remove the interference of imaging in different planes:

[0082] Step 3.1.1) The PC uses a threshold segmentation algorithm to process the vertical illumination image to obtain a square shadow area image;

[0083] Step 3.1.2) PC fits the longer side lines of the two square-shaped shadow areas to obtain a total of four parallel straight lines, and selects the two closest straight lines as the separation lines;

[0084] Step 3.1.3) The PC applies a dividing line to the backlit image, fills the middle part of the dividing line with a white background, and divides the backlit image into two parts, thereby achieving the purpose of removing interference from different plane imaging.

[0085] Step 3.2) After eliminating the interference of different plane imaging, the plane image is processed in regions according to the connectivity relationship. For each sub-region, the PC uses the LSD algorithm to detect the straight contour of the aviation connector. The remaining contours are non-linear contours. A variety of common curve fitting is performed on the non-linear contours to achieve the extraction of the straight contour and curved contour of the edge of the aviation connector base;

[0086] Step 3.3) Based on the scale calibration results obtained in step 1.4), the PC calculates the length of the straight contour and the characteristic size of the curved contour, converts the pixel value into the actual size value, and then realizes the measurement of the external dimensions of the base of the aviation connector.

[0087] Step 4) obtaining the out-of-plane feature image and measuring the size of the out-of-plane feature area.

[0088] The position and orientation of the rounded corner area of ​​the aviation connector are identified by the top-down camera image, the image minimum circumscribed rectangle of a single rounded corner area is obtained, and the rounded corner feature direction descriptor is designed. The long and short sides of the above rectangle are aligned with the imaging plane of the side-view camera in turn, and the out-of-plane feature image is obtained by the side-view camera. The same measurement method as step 3) is used to perform precise size measurement of the out-of-plane feature area of ​​the aviation connector.

[0089] In one achievable manner, the process of measuring the dimensions of the non-planar feature area of ​​an aviation connector may include the following steps:

[0090] Step 4.1) PC segments the rounded corner area based on the rounded corner shadow image extracted from the top-view camera image, calculates the minimum enclosing rectangle of a single rounded corner area, calculates the angles α and β between its long and short sides and the positive direction of the X-axis, and calculates the area S of the shadow image corresponding to the rounded corner area, and constructs the rounded corner feature direction descriptor (α, β, S);

[0091] Step 4.2) The PC rotates the aviation connector clockwise by an angle of α and counterclockwise by an angle of (1-β) according to the rounded corner feature descriptor, so that the long side and the short side of the rectangle are aligned with the imaging plane of the side-view camera, and obtains the out-of-plane feature image through the side-view camera;

[0092] Step 4.3) During the rotation process of step 4.2), the PC uses the affine transformation principle to calculate the additional displacement caused by the rotation, and instructs the MCU to drive the electric loading platform to reset the position of the aviation connector to the position before the rotation, and at the same time, fine-tune the position of the aviation connector according to the area S in the fillet feature descriptor to ensure that the area of ​​the fillet area remains unchanged;

[0093] Step 4.4) The PC determines the clarity of the image according to the Laplace value of the image, and uses the PID algorithm to fine-tune the electric loading platform in a direction perpendicular to the side-view camera according to the clarity, so that the side-view camera image is clear;

[0094] Step 4.5) After the characteristic surface of the aviation connector coincides with the imaging plane of the side-view camera, the PC uses the same method as step 3.2) to extract the edge straight line and curve contour of the support plate plane of the aviation connector, and then measures the external dimensions of the support plate plane of the aviation connector. The effect of the dimension measurement is as follows: Figure 6 shown.

[0095] like Figure 1 , Figure 2 As shown, an embodiment of the present invention further provides a dimension measurement system for a support plate type aviation connector, comprising: a light source time-sharing control system, an MCU, a PC, and an electric loading platform.

[0096] MCU is connected to the light source time-sharing control system and PC, and the light source time-sharing control system is connected to PC.

[0097] The electric loading platform is arranged below the backlight source of the overhead camera and is connected to the MCU.

[0098] In one embodiment, the light source time-sharing control system includes: a top-view camera, a side-view camera, a backlight illumination system, and a vertical illumination system;

[0099] The backlight illumination system includes a backlight source for a top-view camera disposed below the aviation connector and a backlight source for a side-view camera disposed on the side of the aviation connector;

[0100] The vertical lighting system includes a group of strip light sources installed on both sides of the top-view camera and the side-view camera.

[0101] In summary, the present invention provides a dimension measurement system and method for support plate type aviation connectors, which mainly include a light source time-sharing control system for imaging with differences in the same position, automatic position adjustment of aviation connector visual inspection based on rounded corner areas, an algorithm for eliminating non-planar images and plane dimension measurement of connector bases, and an aviation connector spatial positioning and non-planar dimension measurement algorithm based on rounded corner features; the present invention first proposes a light source time-sharing control system for imaging with differences in the same position, realizing automatic switching between the main light source and the strip light source, ensuring that images of parts under different lighting environments at the same position are obtained separately; an automatic position adjustment method for visual inspection of aviation connectors based on rounded corner areas adopts the linkage of vision and electric loading platforms based on rounded corner features, adjusts the position of the workpiece to be identified according to the number and area of ​​the rounded corner areas, and ensures that the plane image of the aviation connector base is completely obtained; an algorithm for eliminating non-planar images and plane dimension measurement of aviation connector bases realizes accurate measurement of the plane dimensions of non-planar connector bases that only contain information in the camera imaging plane; an aviation connector spatial positioning and non-planar dimension measurement algorithm based on rounded corner features accurately locates the non-planar features of non-planar connectors through rounded corner features, and obtains the dimensions of the spatial feature surfaces of the connectors in sequence.

[0102] In order to verify the feasibility and effectiveness of the system and method of the present invention, an experiment is conducted on a typical scenario and the accuracy of the method is evaluated.

[0103] For example, five sizes of aviation connectors were tested, and the size estimation results are shown in Table 1:

[0104] Table 1 Aircraft connector image data

[0105]

[0106] According to the test data, the measurement error of the method and system proposed in the present invention is within 0.3 mm, which can meet the accuracy requirements.

[0107] The above only expresses the implementation mode of the present invention, and its description is relatively specific and detailed, but it cannot be understood as limiting the scope of the patent. It should be pointed out that for ordinary technicians in this field, several modifications and improvements can be made without departing from the concept of the present invention, which all belong to the protection scope of the present invention. In addition, the parts not detailed in the present invention are all conventional technologies.

Claims

1. A method for measuring the dimensions of a support plate type aviation connector, characterized in that: The method comprises: Step 1: Use a light source time-sharing control system for imaging differences at the same position to obtain a complete set of spatial position images of aviation connectors; Step 2: Obtain fillet features of aviation connectors; Step 3, remove the out-of-plane images and measure the plane dimensions of the connector base; Step 4: Obtain the out-of-plane feature image and measure the size of the out-of-plane feature area.

2. The method according to claim 1, characterized in that The process of building a light source time-sharing control system and obtaining differential images of aviation connectors in different lighting environments at the same location includes: Step 1.1) Build a backlighting system: Place main light sources under and on the side of the aviation connector as the backlighting light sources for the top-view camera and the side-view camera, and use parallel backlighting; Step 1.2) Build a vertical lighting system: Install a set of strip light sources on both sides of the top-view camera and the side-view camera, and calibrate the direction of each light source to ensure that the light hits the surface of the aviation connector vertically; Step 1.3) Automatically switch the backlight source and the strip light source through time-sharing control technology to obtain difference images of the aviation connector under different lighting environments at the same position.

3. The method according to claim 2, characterized in that Step 1.3) specifically includes: Step 1.3.1) In the initial state, the MCU controls the backlight source to switch from the off state to the on state, and the strip light source is in the off state; after the camera takes a photo, a first signal indicating that the photo acquisition is completed is sent to the PC, wherein the camera is a top-view camera and a side-view camera; Step 1.3.2) After the PC receives the first signal sent by the camera indicating that the photo collection is complete, the PC sends a first control signal to the MCU. The MCU controls the backlight source to turn off and the strip light source to turn on. After the camera takes a photo again, the PC sends a second signal indicating that the photo collection is complete. Step 1.3.3) After the PC receives the second signal sent by the camera to indicate that the photo acquisition is completed, it sends a second control signal to the MCU, and the MCU controls the strip light source to turn off, completing a photo cycle; through a photo cycle, the backlight illumination image and the vertical illumination image of the same position in a single direction can be obtained. The overhead camera and the side view camera respectively perform the above-mentioned photo cycle operations to obtain a complete set of spatial position images of aviation connectors.

4. The method according to claim 2, characterized in that: After step 1.3), it also includes: Step 1.4) Adjust the imaging area of ​​the top-view camera and the side-view camera so that when the strip light source is turned on, the imaging area of ​​the camera does not include the reflected light from the surface of the backlight source; calibrate the camera.

5. The method according to claim 1, characterized in that: Step 2 specifically includes: Step 2.1) The PC uses a threshold segmentation algorithm to obtain a square shadow area image based on the overhead image of the aviation connector at the same position under different lighting environments obtained in step 1, counts the number of square shadow areas detected, and automatically adjusts the position of the aviation connector according to the number of square shadow areas detected; Step 2.2) If there is only one square shadow area detected, adjust the number of rounded corners at the position of the aviation connector: the PC obtains an edge straight line by fitting the long side of the rectangular enclosing frame of the square shadow area, calculates a unit direction vector perpendicular to the straight line, and points to the square shadow area. According to the unit direction vector, the MCU is instructed to drive the electric loading platform to move; the center of the rectangular enclosing frame is moved to the center of the camera field of view to ensure that two rounded corner areas can be identified; Step 2.3) If the number of detected square shadow areas is two, the position difference adjustment of the aviation connector position is performed: the vertical illumination video of the aviation connector is input through the camera's video stream mode, and the PC calculates the pixel areas of the two detected square shadow areas in real time. If the pixel area difference between the two square shadow areas is less than the set threshold, the position adjustment is stopped; otherwise, the edge straight line is obtained by fitting the long sides of the square shadow areas, and the unit direction vector perpendicular to the straight line is calculated and points to the direction of the larger shadow area. According to the unit direction vector, the MCU is instructed to drive the electric carrier to move.

6. The method according to claim 4, characterized in that Step 3 specifically includes: Step 3.1) After the electric loading platform finishes position adjustment, the PC processes the two images acquired by the overhead camera under different lighting conditions at the same position to remove interference from different plane imaging: Step 3.2) After eliminating the interference of different plane imaging, the plane image is processed in regions according to the connectivity relationship. For each sub-region, the PC detects the straight contour of the aviation connector, and the remaining contours are non-linear contours. The non-linear contours are curve fitted to achieve the extraction of the straight contour and curved contour of the edge of the aviation connector base; Step 3.3) Based on the scale calibration results obtained in step 1.4), the PC calculates the length of the straight contour and the characteristic size of the curved contour, converts the pixel value into the actual size value, and then realizes the measurement of the external dimensions of the base of the aviation connector.

7. The method according to claim 6, characterized in that Step 3.1) specifically includes: Step 3.1.1) The PC uses a threshold segmentation algorithm to process the vertical illumination image to obtain a square shadow area image; Step 3.1.2) PC fits the longer side lines of the two square-shaped shadow areas to obtain a total of four parallel straight lines, and selects the two closest straight lines as the separation lines; Step 3.1.3) The PC applies a dividing line to the backlit image, fills the middle part of the dividing line with a white background, and divides the backlit image into two parts, thereby achieving the purpose of removing interference from different plane imaging.

8. The method according to claim 1, characterized in that Step 4 specifically includes: Step 4.1) PC segments the rounded corner area based on the rounded corner shadow image extracted from the top-view camera image, calculates the minimum enclosing rectangle of a single rounded corner area, calculates the angles α and β between its long and short sides and the positive direction of the X-axis, and calculates the area S of the shadow image corresponding to the rounded corner area, and constructs the rounded corner feature direction descriptor (α, β, S); Step 4.2) The PC rotates the aviation connector clockwise by an angle of α and counterclockwise by an angle of (1-β) according to the rounded corner feature descriptor, so that the long side and the short side of the rectangle are aligned with the imaging plane of the side-view camera, and obtains the out-of-plane feature image through the side-view camera; Step 4.3) During the rotation process of step 4.2), the PC calculates the additional displacement caused by the rotation and instructs the MCU to drive the electric loading platform to reset the position of the aviation connector to the position before the rotation. At the same time, the position of the aviation connector is fine-tuned according to the area S in the fillet feature descriptor to ensure that the area of ​​the fillet area remains unchanged; Step 4.4) The PC determines the clarity of the image and fine-tunes the electric loading platform in a direction perpendicular to the side-view camera so that the side-view camera image is clear; Step 4.5) After the characteristic surface of the aviation connector coincides with the imaging plane of the side view camera, the PC extracts the edge straight lines and curve contours of the support plate plane of the aviation connector according to step 3.2), thereby completing the measurement of the external dimensions of the support plate plane of the aviation connector.

9. A dimension measurement system for support plate type aviation connectors, characterized in that: The method according to any one of claims 1 to 8 is adopted, wherein the system comprises: a light source time-sharing control system, an MCU, a PC, and an electric loading platform. MCU is connected to the light source time-sharing control system and PC, and the light source time-sharing control system is connected to PC. The electric loading platform is arranged below the backlight source of the overhead camera and is connected to the MCU.

10. The system according to claim 9, characterized in that The light source time-sharing control system includes: overhead camera, side-view camera, backlight illumination system, and vertical illumination system; The backlight illumination system includes a backlight source for a top-view camera arranged below the aviation connector and a backlight source for a side-view camera arranged on the side of the aviation connector; The vertical lighting system includes a group of strip light sources installed on both sides of the top-view camera and the side-view camera.

Images