Real-time decoding positioning method for coded targets of a gap measurement system

Abstract

The present application belongs to the technical field of target real-time decoding positioning, and provides a kind of encoding target real-time decoding positioning method of slit measurement system, its steps include: S1 the layout of encoding target of slit detection point;S2 for the binary coding of encoding target image shot at large inclination angle, and the center position of encoding area and positioning area is obtained as the initial point of compression transformation;S3 adopts single direction wide edge detection to combine edge projection method, and is compressed to project transformation to encoding target point;S4 encoding target decoding;S5 subpixel positioning of encoding target edge pixel optimization, the present application provides edge projection benchmark using single direction wide edge detection, reduces the influence of compression projection transformation by large inclination angle shooting, realizes the compression target point projection transformation using edge projection, and the edge of positioning area is combined with the edge of encoding target, reduces the edge mis-extraction rate, improves the subpixel positioning precision, while having the characteristics of fast and real-time, suitable for long slit multi-point detection.

Description

TECHNICAL FIELD

[0001] The present application belongs to the technical field of target real-time decoding positioning, and particularly relates to a coding target real-time decoding positioning method of a gap measurement system. BACKGROUND

[0002] The coding target decoding and positioning method of the gap measurement system is based on the technical requirement of real-time dynamic detection of gap state, adopts a binocular measurement device, arranges coding targets on both sides of the gap to be detected, realizes real-time decoding and positioning of the coding targets, and finally calculates the spatial distance of the gap. In actual engineering application environment, the installation space is limited, which usually brings large-angle shooting of the measurement device and limitation of the area of the coding target, that is, the coding target design needs to be simplified, and the decoding and positioning algorithm of the coding target needs to be accurate and real-time. Solving the problem of large-angle shooting and fast and accurate decoding and positioning of the simplified target is the key to ensuring fast, real-time and accurate measurement of the gap measurement system.

[0003] The following technical problems exist in actual engineering gap measurement:

[0004] 1. Actual working environment: In actual engineering application environment, the installation space of the measurement system is limited, which usually brings large-angle shooting, especially for long gap multi-position point detection. The measurement device is usually installed at a certain position, which also leads to large-angle shooting. In order to ensure the accuracy of gap measurement, the decoding and positioning of the coding target need to have high accuracy during large-angle shooting.

[0005] 2. Limited size of coding target: In actual engineering application environment, the layout space of the coding target is also limited, which requires the use of smaller size coding target to realize accurate decoding and positioning.

[0006] 3. Real-time requirement: In actual engineering application, the measurement of the gap usually requires certain real-time performance. The decoding of the rich coding information of the coding target brings huge recognition algorithm operation amount, which requires simplifying the coding target and using simple algorithm to realize accurate decoding and positioning.

[0007] 4. The decoding accuracy of the target of the traditional algorithm for large-angle shooting is low. The target design usually increases the positioning symbol or increases the coding target layer to improve the decoding accuracy. However, the complex target design increases the size of the target and brings complex algorithm. In actual engineering, the real-time measurement requirement cannot be met, and the limited space cannot realize the target layout, which leads to the failure of measurement.

[0008] The above technical difficulties limit the use of the decoding and positioning method of the existing mature coding target, especially in actual engineering applications, the gap measurement system is applied in the airborne environment, the target installation layout space and the measurement equipment installation space are limited, so that the size of the target is limited in the range and the measurement equipment is shot at a large angle, which requires a simple coding target to quickly, real-time and accurately realize gap measurement at a large angle. The commonly used mature algorithm cannot achieve this requirement, firstly, the commonly used mature algorithm has low decoding accuracy for the coding target shot at a large angle, and the gap measurement will be wrong, and secondly, in order to improve the decoding accuracy of the coding target, the positioning symbol is increased or the coding target layer is increased during target design, that is, the target size is increased and the identification of the complex algorithm is also brought, which leads to a serious decrease in extraction speed and cannot meet the real-time requirement, especially for long gap multi-position detection, with the increase of the number of coding targets, the algorithm operation amount will be multiplied, and only the measurement after operation can be realized. Therefore, it is necessary to provide a coding target real-time decoding and positioning method of a gap measurement system. SUMMARY

[0009] In view of the problems in the prior art, the application provides a coding target real-time decoding and positioning method of a gap measurement system, which adopts single-direction wide-edge detection to provide edge projection reference, reduces the influence of large-angle shooting on compressed projection transformation, selects the gap vertical direction as the single-direction edge to avoid the gap edge, adopts edge projection to realize compressed target point projection transformation, does not need to additionally increase the positioning symbol or the coding layer of the target during target design when shooting at a large angle, adopts edge pixel optimization to combine the edges of the positioning area and the coding target, reduces the edge mis-extraction rate through mutual constraint, improves the sub-pixel positioning precision, has the characteristics of rapidness and real-time, and has engineering practicability, especially for long gap multi-point detection.

[0010] The coding target real-time decoding and positioning method of the gap measurement system comprises the following steps:

[0011] S1, coding target layout of gap detection points: m coding targets are arranged on both sides of the gap to be measured, and correspond to the targets on both sides of the gap, a binocular vision system is adopted for the measurement system, and is arranged above the gap to be measured to shoot the images of 2m coding targets 2 at a large angle in real time;

[0012] S2, extracting compressed projection transformation initial point: the target image in step S1 is subjected to binaryzation processing, the positioning area and the coding area of 2m coding targets are segmented, and the center position pixel coordinates of the positioning area are preliminarily extracted: p i (i = 1, 2,..., 2m), and the center position pixel coordinates of the coding area are: i is the i-th coding target, n is the number of coding regions of the i-th coding target, and n≥8 is used as the initial point of the compressed projection transformation;

[0013] S3. Extract the target points of the compressed projection transformation: Use a single-direction wide edge detection combined with the edge projection method to perform compressed projection transformation on the center points of the coded area and the positioning area.

[0014] S4. Encoded target decoding, specifically including:

[0015] S41. The target point p′ in the localization region of the i-th coded target. i (i = 1, 2, ..., 2m) Draw a straight line parallel to the X-axis.

[0016] S42. Sequentially calculate the center target point of the localization region passing through the i-th coded target and its corresponding p′. i (i = 1, 2, ..., 2m) Center target point of the coding region straight line

[0017] S43, Seeking and The included angle If the y-coordinate of the compression transformation target point at the center of the coding region of the i-th coding target is greater than the line L i x The y-coordinate, then

[0018] S44 If the angle region is encoded as 1, then the encoded value of the encoded target is calculated.

[0019] S5. Sub-pixel localization for optimized edge pixels of the encoded target, specifically including:

[0020] S51. Refine the wide edge region of the i-th encoded target. Find the center line from the edge.

[0021] S52, respectively on the straight line Take k points for the upper average and Where k is an even number and k≥10;

[0022] S53, with and and and For each pair of corresponding points, find the coordinates of the center point of the line connecting them.

[0023] S54. Determine the pixel coordinates p of the center position of the region initially located in step S2. i Is it in If the value is not within the specified range, then search for p again. i and The point is located within this range; if it is within the range, the centroid method is used to find the sub-pixel localization center, thus achieving sub-pixel localization of the coded target.

[0024] Preferably, step S3 includes the following sub-steps:

[0025] S31. Perform unidirectional wide edge detection on the binarized image described in step S2, and detect the two wide edges of each coded target perpendicular to the gap. Where i represents the i-th encoded target;

[0026] S32. Calculate the center position p of the entire positioning area. i (i = 1, 2, ..., 2m) and the center position of all coded regions Each line The distance; if the distance is less than a certain threshold T, then the center of the positioning area, the center of the coding area, and the straight line are determined to belong to the same coding target;

[0027] S33. The two wide edges of each target region are calculated using a scanning method. The four endpoints and Find the points separately and points Distance between point and points Distance between

[0028] S34. Sequentially target the center position p of the positioning area of ​​2m targets. i (i = 1, 2, ..., 2m) and the center position of the coding region Calculate the coordinates of the horizontal projection points respectively Coordinates of the projection point in the vertical direction Where i is the i-th encoded target, and q is the q-th projection point of the i-th encoded target;

[0029] S35, sequentially targeting the center position p of the positioning area for 2m targets. i (i = 1, 2, ..., 2m) and the center position of the coding region Calculate the coordinates of the projection points in the vertical direction respectively.

[0030]

[0031] S36, sequentially calculating the center position p of the positioning area of the 2m targets i (i = 1, 2,... 2m) and the center position of the encoding area respectively calculating the target point p' of the corresponding compressed projection transformation i (i = 1, 2,... 2m) and The calculation formula is:

[0032]

[0033] In the formula, a i is the scaling factor of the i-th target point, is the x-coordinate value of the upper left point of the i-th target point, is the y-coordinate value of the upper right point of the i-th target point, is the distance between the q-th center position of the i-th target point in the horizontal direction and the projection point and the upper left point , is the distance between the q-th center position of the i-th target point in the vertical direction and the projection point and the upper right point , is the minimum value of and in the i-th target.

[0034] Preferably, the width of the single direction wide edge detection in step S31 is greater than 3 pixels.

[0035] Preferably, the same encoding target determined in step S32 includes one positioning area center position p i , a group of encoding area center positions , and two straight lines

[0036]

[0037] Preferably, the horizontal projection coordinate of the q-th point of the i-th encoding target in step S34 is solved as:

[0038] S341, solving the straight line equation of the straight line passing through the q-th point and parallel to the straight line

[0039] S342, solving the straight line equation of the straight line passing through the point and the point

[0040] S343, solving the straight line and the straight line ​​​The intersection point is the horizontal projection coordinate of the q-th point of the i-th coded target.

[0041] Preferably, the coordinates of the projection point in the vertical direction of step S35 are... The solution is:

[0042] S351, Solve for a line that passes through point q and is parallel to the line. equation of the straight line

[0043] S352, Solving for a straight line With a straight line The intersection point is the coordinate of the vertical projection point of the q-th point of the i-th coded target.

[0044] Preferably, the scaling factor α of the i-th encoded target in step S36 is... i The value ranges from 0.8 to 1.

[0045] Compared with the prior art, the present invention has the following beneficial technical effects:

[0046] 1. The real-time decoding and positioning method of the coded target in the gap measurement system of the present invention adopts a single-direction wide edge detection to provide an edge projection reference, which reduces the influence of large tilt angle shooting on the compression projection transformation. At the same time, the single-direction edge selection is perpendicular to the gap, avoiding the gap edge, so the algorithm is not affected by gap interference. Combined with wide edge detection, the area is easy to mark, which reduces the amount of algorithm computation and further improves the decoding accuracy.

[0047] 2. The real-time decoding and positioning method for the coded target in the gap measurement system of this invention uses edge projection to achieve compressed projection transformation for the positioning center position and the coding center position point. When shooting at large tilt angles, there is no need to add additional locators or target coding layers to the target design. The target design is simple and the target size is miniaturized, making the target placement less restricted by space. The algorithm transforms the positioning center position and the coding center position, no longer using affine transformation of the entire image. Especially when detecting multiple positions in long gaps, the algorithm is simplified, improving the computing speed while meeting the requirements of accurate decoding at large tilt angles, and is more valuable for engineering applications.

[0048] 3. The real-time decoding and positioning method of the coded target in the gap measurement system of the present invention adopts edge pixel optimization for sub-pixel positioning, so that the edge of the positioning area is combined with the edge of the coded target, mutually constraining each other, reducing the edge false extraction rate, and further improving the sub-pixel positioning accuracy.

[0049] 4.The real-time decoding positioning method of the coded target of the gap measurement system of the present application, which can realize real-time measurement of the gap of automatic docking, the gap of a hatch door, the gap of an elevator door, etc., has good engineering use value, small amount of calculation, good robustness of decoding sub-pixel positioning, and is suitable for various engineering applications of large inclination measurement and long gap measurement with limited installation layout, and can be applied to more systems while the basic principle remains unchanged. BRIEF DESCRIPTION OF DRAWINGS

[0050] Figure 1 A flowchart of the real-time decoding positioning method of the coded target of the gap measurement system of the present application is shown.

[0051] Figure 2 A layout diagram of the coded target in the real-time decoding positioning method of the coded target of the gap measurement system of the present application is shown.

[0052] Figure 3 A single-direction wide edge diagram in the real-time decoding positioning method of the coded target of the gap measurement system of the present application is shown.

[0053] Figure 4 A wide edge, four end points, and and of the i-th coded target in the embodiment of the present application are shown.

[0054] Figure 5 A wide edge, four end points, and of the i-th coded target in the embodiment of the present application are shown.

[0055] Figure 6 An angle between the center of the coding area and the X-axis after compression transformation in the embodiment of the present application is shown.

[0056] Figure 7 An edge-optimized sub-pixel positioning diagram in the embodiment of the present application is shown.

[0057] MAIN REFERENCE NUMBERS:

[0058] A gap to be measured 1, a coded target 2, and a measurement system 3. DETAILED DESCRIPTION

[0059] To fully understand the technical content, structural features, purposes achieved, and effects of the present application, the following will be described in detail in combination with the drawings of the specification.

[0060] As shown in Figure 1 , the pose measurement method of the automatic alignment system of the embodiment of the present application includes the following steps:

[0061] S1, m encoding targets 2 are arranged on both sides of the gap to be measured 1, and the targets on both sides of the gap correspond to each other, and a binocular vision system is used as the measurement system 3, which is installed above the gap to be measured 1 and photographs the images of the 2m encoding targets 2 in real time at a large inclination angle.

[0062] The arrangement of the encoding targets on both sides of the gap in the application example is shown in the figure. Figure 2 The encoding target is designed by taking a circle as a basic element, which is composed of a center positioning circle and a peripheral encoding circle (8 bits), and the counterclockwise direction is defined as the positive direction. The encoding circle obtains 8-bit binary encoding, and the smallest value is selected as the encoding value after 7 times of cyclic shift. The size of the marking peripheral of the scheme is 20mm*20mm, the diameter of the center positioning circle is 6mm, and the diameter of the encoding circle is 3mm. In the application example, the camera is photographed at an inclination angle of 60°.

[0063] S2, the photographed target image is subjected to binaryzation processing, and the center position pixel coordinates p i (i=1, 2,... 2m) of the positioning area of all 2m encoding targets and the center position pixel coordinates (i is the i-th encoding target, n is the number of encoding areas of the i-th encoding target, and n≥8) are extracted as initial points of the compressed projection transformation.

[0064] In the application example, 5 encoding targets are arranged on both sides of the gap. The collected images are subjected to binaryzation processing by using the maximum inter-class variance method, and all 10 encoding targets are segmented, and 10 groups of center position coordinates of the center circles of the 10 encoding targets and 37 groups of center position coordinates of the small circles around the center circles of the 10 encoding targets are extracted.

[0065] S3, the target points of the compressed projection transformation are extracted based on the single-direction wide edge detection combined with the edge projection method, which includes the following sub-steps:

[0066] S31, the binaryzation image of step S2 is subjected to single-direction wide edge detection, and two wide edges of each encoding target perpendicular to the gap are detected Wherein i represents the i-th encoding target.

[0067] S32, the center positions p i (i=1, 2,... 2m) of all positioning areas and the center positions of all encoding areas are calculated, respectively. The distances between the center positions and the center positions of each straight line

[0068] S33, scanning two wide edge regions and extracting two wide edges of each target region four end points of the two wide edges and respectively calculating the distance between point and point point and point

[0069] In this application example, for the 10 targets on both sides of the gap, the Sobel edge detection method with a width of 3 pixels is used to extract the target edges perpendicular to the gap direction, a total of 20 wide edges are extracted, as shown in Figure 3 The threshold value T is selected according to the length of a single edge, and in this example, T = 40 is selected to determine the same target. Taking the 8th coded target as an example, its wide edge, four end points, and and as shown in Figure 4

[0070] S34, sequentially calculating the horizontal projection point coordinates of the center positions p i (i = 1, 2,... 2m) and the center positions of the coded regions of the 2m targets where i represents the ith coded target, and q represents the qth projection point of the ith coded target.

[0071] S341, solving the equation of the straight line passing through the qth point and parallel to the straight line

[0072] S342, solving the equation of the straight line passing through the points and

[0073] S343, solving the intersection point of the straight line and the straight line , which is the qth point horizontal projection coordinate of the ith coded target

[0074] S35, sequentially calculating the vertical projection point coordinates of the center positions p i (i = 1, 2,... 2m) and the center positions of the coded regions

[0075] of the 2m targets Solving as follows: ​​​​​​

[0076] S351, solving the straight line equation passing through the qth point of the ith target and parallel to the straight line

[0077] S352, solving the intersection point of the straight line and the straight line , which is the vertical projection point coordinate of the qth point of the ith coded target

[0078] S353, sequentially calculating the target point p' i (i = 1, 2,... 2m) and the center position of the coding area p' of the positioning area of the 2m targets and calculating the target point p' i (i = 1, 2,... 2m) and The calculation formula is:

[0079]

[0080] In the formula, α i is the scaling factor of the ith target point, usually 0.8-1. is the x-coordinate value of the upper left point of the ith target point, is the y-coordinate value of the upper right point of the ith target point, is the distance between the qth center position of the ith coded target point in the horizontal direction and the upper left point , is the distance between the qth center position of the ith target point in the vertical direction and the upper right point , is the minimum value of and . In this application example, the 8th coded target is taken as an example, assuming that the number of the leftmost coded small circle is 1, then the as shown in

[0081] . Figure 5

[0082] S4, decoding the coded target, specifically including:

[0083] S41, making a straight line parallel to the X-axis through the positioning area center target point p' i (i = 1, 2,... 2m) of the ith coded target

[0084] S42, sequentially solving the positioning area center target point of the ith coded target and each p' i ​​​(i = 1, 2, ..., 2m) Center target point of the coding region straight line

[0085] S43, Seeking and The included angle If the y-coordinate of the compression transformation target point at the center of the coding region of the i-th coding target is greater than the line... The y-coordinate, then

[0086] S44 If the angle region is encoded as 1, then the encoded value of the encoded target can be calculated.

[0087] S5. Sub-pixel localization for optimized edge pixels of the encoded target, specifically including:

[0088] S51. Refine the wide edge region of the i-th encoded target. Find the center line from the edge.

[0089] S52, respectively on the straight line Take k points for the upper average and Where k is an even number and k≥10.

[0090] S53, with and and and For each pair of corresponding points, find the coordinates of the center point of the line connecting them.

[0091] S54. Determine the pixel coordinates p of the center position of the region initially located in step S2. i Is it in If the value is not within the specified range, then search for p again. i and The point is located within this range; if it is within the range, the centroid method is used to find the sub-pixel localization center, thus achieving sub-pixel localization of the coded target.

[0092] In this invention example, the 8th coded target is taken as an example. The 8th coded target has 4 coded regions. According to the description of steps S41 to S44, after the compression transformation of the center position of the coded target's positioning region and the center position of the coded region, the straight line between the center target point of the positioning region and the center target point of each coded region is... and The included angle like Figure 6 As shown.

[0093] The schematic diagram of sub-pixel positioning center calculation in the present application is shown in Figure 7 The center line of the wide edge is averaged with 10 points, i.e. k=10, and the range is selected as 2 pixels in horizontal and vertical directions. The center positions of 10 groups of positioning circles are fused with the center positions of the positioning areas preliminarily extracted in step S2, and there are totally 11 groups of positions. If the pixel coordinate position difference between every two groups in horizontal and vertical directions is less than 2 pixels, it is considered to be in the range, and the sub-pixel positioning center is calculated by using the centroid method, so as to realize the sub-pixel positioning of the coded target.

[0094] The above-described embodiments are only used to describe the preferred embodiments of the present application, and are not used to limit the scope of the present application. Without departing from the design spirit of the present application, various modifications and improvements of the technical solutions of the present application made by those skilled in the art shall fall into the protection scope determined by the claims of the present application.

Claims

1. A method of real-time decoding positioning of a coded target of a gap measurement system, characterized in that, It comprises the following steps: S1, encoding target layout of gap detection point: m encoding targets are arranged on both sides of the gap to be measured, and a binocular vision system is used for the measurement system, which is arranged above the gap to be measured and shoots 2m encoding target images in real time; S2, extracting compressed projection transformation initial point: the target image of step S1 is binarized to segment out 2m positioning areas and encoding areas of the coded target, and the center pixel coordinates of the positioning areas are preliminarily extracted: p i (i = 1, 2,... 2m), and the center pixel coordinates of the encoding areas are: i is the ith coded target, n is the number of encoding areas of the ith coded target, and n≥8 as the initial point of the compressed projection transformation; S3, extracting compressed projection transformation target point: a single direction wide edge detection combined with edge projection method is used to perform compressed projection transformation on the center position points of the encoding region and the positioning region; S4, encoding target decoding, specifically comprising: S41, center target point p' of the positioning area of the i-th encoding target i (i = 1, 2,... 2m) as a straight line parallel to the X axis S42, sequentially obtain the positioning area center target point of the i-th encoding target and each p' (i=1, 2,... 2m) encoding area center target point of the i-th encoding target i (i=1, 2,... 2m) encoding area center target point straight line S43, obtaining with the angle of if the y coordinate of the compression conversion target point of the center position of the coding region of the i-th coding target is greater than the y coordinate of the straight line then S44、 If the angle region of the angle region code 1 is found, the code value of the coded target is found. S5, sub-pixel positioning of encoding target edge pixel optimization, specifically comprising: S51, refining the wide edge region of the i-th encoding target of the edge, the central straight line is found S52, respectively, take k points on the straight line and and wherein k is an even number and k≥10; S53、to with with with for the corresponding points, the center point coordinates of the connecting line of each pair of corresponding points are calculated S54, judging the pixel coordinate p of the center position of the preliminary positioning area in step S2 i whether in the range, if not in the range, re-searching p i and point until in the range; if in the range, adopting the centroid method to find the sub-pixel positioning center, realizing the sub-pixel positioning of the encoding target.

2. The coded target real-time decoding positioning method of a slit measurement system according to claim 1, characterized in that, Step S3 comprises the following sub-steps: S31, performing single direction wide edge detection on the binary image of step S2 to detect two wide edges of each encoding target perpendicular to the direction of the gap where i represents the i-th encoding target; S32, calculate the center position p of all positioning areas i (i = 1, 2,... 2m) and the center position p of all encoding areas respectively, the distance between each straight line and the center position p of all positioning areas; if the distance is less than a certain threshold T, it is determined that the positioning area center, the encoding area center and the straight line belong to the same encoding target; S33, calculate two wide edges of each target area respectively by scanning method four end points and calculate the distance between point and point respectively the distance between point and point ​ S34, the center position p of the positioning area for 2m targets in turn i (i = 1, 2,... 2m) and the center position of the encoding area The horizontal projection point coordinates are calculated respectively And the projection point coordinates in the vertical direction Where i is the i-th encoding target, and q is the q-th projection point of the i-th encoding target. S35, sequentially for 2m targets, the positioning area center position p i (i = 1, 2,... 2m) and the encoding area center position Respectively calculate the projection point coordinates in the vertical direction S36, sequentially locate the center position p of the region of 2m targets i (i = 1, 2,... 2m) and the center position of the encoding region Calculate the target point p' of the corresponding compression projection transformation respectively i (i = 1, 2,... 2m) and The calculation formula is: In the formula, α i Let be the scaling factor for the i-th target point. Let x be the x-coordinate of the top-left point of the i-th target point. Let y be the y-coordinate of the upper right point of the i-th target. The horizontal projection point of the q-th center position of the i-th target point. and the top left point distance, The projection point of the qth center position of the i-th encoded target point in the vertical direction and the upper right point distance, For the i-th target and The minimum value.

3. The coded target real-time decoding positioning method of a slit measurement system according to claim 2, characterized in that, The width of the single direction wide edge detection in step S31 is greater than 3 pixels.

4. The coded target real-time decoding positioning method of a slit measurement system according to claim 2, characterized in that, The same code target determined in step S32 includes one positioning area center position p i , a set of code area center positions , and two straight lines 5. The coded target real-time decoding positioning method of a slit measurement system according to claim 2, characterized in that, The qth point horizontal projection coordinate of the ith encoding target of step S34 Solving for: S341, solve for the line equation passing through the qth point and parallel to the line ​ S342, solving the point and the line equation of the point ​ S343, solving the straight line the intersection with the straight line is the horizontal projection coordinate of the qth point of the ith encoding target 6. The coded target real-time decoding positioning method of a slit measurement system according to claim 2, characterized in that, The vertical direction projection point coordinate of step S35 Solving for: S351, solving the straight line equation passing through the qth point and parallel to the straight line S351, solving the straight line equation passing through the qth point and parallel to the straight line S352, solving the straight line The intersection of the straight line is the qth point vertical projection point coordinate of the ith encoding target 7. The coded target real-time decoding positioning method of a slit measurement system according to claim 2, characterized by, Scaling factor a of the i-th encoded target in step S36 i Has a value of 0.8-1.

Images