KR20220075290A - System and method for finding lines in an image with a vision system - Google Patents

Abstract

The present invention relates to a method and system for finding multiline features in an image. Two related steps are used to identify line features. The first process computes the x and y components of the gradient field at each image location, projects the gradient field across multiple subregions, and multiple gradients yielding multiple edgepoints with positions and gradients. A plurality of gradient extrema is detected. The second process is to select two edge points, fit a model line to them, and if the edge point slope is consistent with the model, then the full set of inner left layer points whose location and slope match the model ( full set of inlier points). A set is derived that holds the candidate line with the maximum inner left count and leaves outlier points. The process iteratively applies the line fitting operation and a subsequent set of outer layers to find multiple line results. This process can be done on a thorough RANSAC basis.

Description

SYSTEM AND METHOD FOR FINDING LINES IN AN IMAGE WITH A VISION SYSTEM

Related applications

This application is a co-pending provisional US patent application entitled "SYSTEM AND METHOD FOR FINDING LINES IN AN IMAGE WITH A VISION SYSTEM," filed on November 2, 2015, the entire contents of which are incorporated herein by reference. Claims the interests of serial number 62/249,918.

technical field

The present invention relates to machine vision systems, and more particularly to vision system tools for discovering line features in acquired images.

BACKGROUND Machine vision systems (also referred to herein simply as “vision systems”) are used for many tasks in manufacturing, logistics, and industry. These operations may include inspection of surfaces and parts, alignment of objects during assembly, reading of patterns and ID codes, and any other operations in which visual data is acquired and interpreted for use in further processes. Vision systems typically use one or more cameras to acquire an object of interest or an image of a scene containing the object of interest. This object/object may be stationary or relatively movable. Movement may be controlled by information derived by a vision system, such as when manipulating parts by a robot.

A common task of vision systems is to discover and characterize line features in images. Several tools are used to identify and analyze these line features. In general, this tool relies on sharp contrast differences that occur in parts of the image. Analyze this contrast difference using, for example, a caliper tool to determine whether individual points in the image with the contrast difference can be assembled into line-like features. If it can be assembled, a line is identified in the image. In particular, a tool for finding edge points and a tool for attempting to fit a line to the points are independent of each other. This increases processing overhead and reduces reliability. If the image contains multiple lines, these tools may have limited ability to accurately identify these lines. Furthermore, traditional line-finding tools designed to find a single line in an image can be problematic to use when the image contains multiple closely spaced lines with similar orientation and polarity.

SUMMARY OF THE INVENTION The present invention overcomes the shortcomings of the prior art by providing a system and method for discovering line features in an image that can efficiently and accurately identify and characterize multiple lines. First, the process computes the x- and y-components of the gradient field at each location in the image, projects the gradient field over a plurality of image subregions, and each subregion Detects a plurality of gradient extrema in the , yielding a plurality of edge points with associated positions and gradients. Next, the process iteratively selects two edge points, fits a model line to these edge points, and if the gradients of these edge points are consistent with the model line, the location coincident with the model line. Compute the entire set of inlier points with gradients and . The candidate line with the maximum outlier count is retained as the line result, and the remaining set of outlier points are derived. The process iteratively applies a line fitting operation to this set of outliers and subsequent sets of outliers to discover multiple line results. The line-fitting process may be performed throughout, or may be based on a random sample consensus (RANSAC) technique.

In an exemplary embodiment, a system for finding line features in an acquired image is provided. The vision system processor receives image data of the scene including the line features. An edge point extractor generates intensity gradient images from the image data, and finds edge points based on the intensity gradient images. A line-finder fits the edge points to one or more lines based on an intensity gradient at the edge points. Illustratively, the line finder operates a RANSAC-based process of fitting outlier edge points to new lines, including iteratively defining lines from outlier edge points to a previously defined line. The edge point extractor performs a gradient field projection of the line-feature-containing regions of the intensity gradient images. Exemplarily, the gradient-field projection is oriented along a direction established in response to one or more or expected orientations of the line features, wherein the gradient-field projection defines a granularity based on a Gaussian kernel. can Illustratively, the image data may include data from a plurality of images acquired from a plurality of cameras and transformed into a common coordinate space. The image data may also be smoothed using a smoothing (weighting) kernel, which may include a 1D Gaussian kernel or other weighting function. The edge points may be selected based on a threshold defined by absolute contrast and a normalized contrast based on an average intensity of the image data. Illustratively, the line finder exchanges edge points representing portions of parallel lines or intersecting lines to correct an erroneous orientation, and/or a line based on gradient values of the edge points. Constructed and arranged to identify lines with polarity variation, including mixed polarities of features. Also illustratively, the edge point extractor is arranged to find a plurality of gradient magnitude maxima in each of the gradient projection sub-regions. Each of these gradient magnitude maxima can be identified as some of the plurality of edge points, and can be described by a position vector and a gradient vector. Additionally, the line finder determines a consistency between at least one of the extracted plurality of edge points and at least one candidate line of the found plurality of lines by calculating a metric. can be arranged to determine. The metric may be based on a distance of the at least one edge point from the candidate line and an angular difference between a gradient direction of the edge point and a normal direction of the candidate line.

DETAILED DESCRIPTION OF THE INVENTION The following description of the invention refers to the accompanying drawings.
1 depicts an exemplary vision system arrangement for acquiring an image of an object, including a vision system processor and multiple edge features including an edge-discovery tool/module, in accordance with an exemplary embodiment;
Fig. 2 shows an overview of a system and method for extracting edge points and finding lines from acquired images, in accordance with an exemplary embodiment;
3 is a flow diagram of a procedure for extracting an edge point according to the system and method of FIG. 2;
FIG. 4 depicts a gradient field projection on a region of an image containing edge features that is part of the procedure for extracting edge points of FIG. 3 ; FIG.
Fig. 5 shows the application of a Gaussian kernel to an image to smooth the image, for use in the procedure for extracting edge points of Fig. 3;
FIG. 6 shows a gradient field projection comprising applying a Gaussian kernel to smooth the projection for use in the procedure for extracting edge points of FIG. 3 ; FIG.
FIG. 7 graphically illustrates an overview of the procedure for extracting the edge point of FIG. 3 , comprising applying Gaussian kernels and calculating an absolute contrast threshold and a normalized contrast threshold for the edge points; FIG.
8 is a graph showing a region of qualified contrasts for edge points, with a sufficient absolute contrast threshold and a normalized contrast threshold;
Fig. 9 is a flow diagram of a procedure for discovering a line based on edge points found in Fig. 3 using the exemplary RANSAC process in accordance with an exemplary embodiment;
10 and 11 show erroneous and correct alignment of edge points for closely spaced parallel line features, respectively;
12 and 13 respectively illustrate correct and erroneous alignment of edge points for intersecting line features that can be analyzed according to the line-finder of an exemplary system and method;
14-17 illustrate light-to-dark polarity, dark-to-polarity that can be analyzed according to the line-finder of exemplary systems and methods. Figures each showing examples of lines representing either polarity of light polarity), light to dark polarity or dark to bright polarity, or a mixed polarity thereof; and
Fig. 18 shows a change in coverage score for a line found taking into account a user-defined mask;

An exemplary vision system arrangement 100 that may be used in accordance with an exemplary embodiment is shown in FIG. 1 . System 100 includes at least one vision system camera 110 , and may include one or more additional optional cameras 112 (shown in dashed lines). Exemplary camera(s) 110 , 112 include an image sensor (or imager) S and associated electronics that acquires image frames and transmits the image frames to a vision system process (processor) 130 . ), and this image frame may be instantiated in an independent processor and/or computing device 140 . Camera 110 (and 112 ) includes suitable lenses/optics 116 to focus on the scene containing object 150 under examination. Camera 110 (and 112 ) may include internal and/or external illuminators (not shown) that operate in accordance with an image acquisition process. Computing device 140 may be any acceptable processor-based system capable of storing and manipulating image data in accordance with example embodiments. For example, computing device 140 may include a PC (shown), server, laptop, tablet, smartphone, or other similar device. Computing device 140 may include suitable peripherals such as a bus-based image capture card interconnected to the camera. In alternative embodiments, the vision processor may be partially or completely contained within the camera body itself and may be networked with other PCs, servers and/or camera-based processors that share and process image data. Computing device 140 optionally selects an appropriate display 142 that can support vision system tools provided to vision system processor (processor) 130 and a suitable graphical user interface (GUI) that can operate in accordance with processor 132 . can be included as It is understood that the display may be omitted in various embodiments and/or provided only for setup functions and service functions. The vision system tool may be any acceptable software and/or acceptable for use in inspecting an object, such as commercially available from Cognex Corporation of Natick, Massachusetts. It can be part of a hardware package. The computing device may include associated user interface (UI) components including, for example, a keyboard 144 and a mouse 146 , and a touchscreen in the display 142 .

The camera(s) 110 (and 112 ) images some or all of the object 150 positioned within the scene. Each camera defines an optical axis OA around which a field of view is established based on optics 116 , focal length, and the like. The object 150 includes a plurality of edges 152 , 154 and 156 each arranged in several directions. For example, the object edges may include an edge of a cover glass mounted within the smartphone body. Illustratively, the camera(s) may image an entire object or a specific location (eg, a corner where the glass meets the body). A (common) coordinate space may be established for the object, one of the cameras, or another reference point (eg, a moving stage supporting the object 150 ). As shown, the coordinate space is represented by axes 158 . These axes define an exemplary orthogonal x-axis, y-axis and z-axis, and rotation (θ _z ) about the z-axis in the xy plane.

According to an exemplary embodiment, vision system process 130 interacts with one or more applications/processes (executed on computing device 140 ) that collectively include a set of vision system tools/processes 132 . It works. These tools may include several conventional specialized applications used to analyze image data - for example, using various calibration tools and affine transform tools to transform the acquired image data. It can be transformed into a predetermined (eg common) coordinate system. Tools may be included to convert image grayscale intensity data to a binary image based on a predetermined threshold. Additionally, tools may be provided to analyze gradients in intensity (contrast) between adjacent image pixels (and subpixels).

Vision system process (processor) 130 includes a line-discovery process, tool, or module 134 that finds multiple lines in an acquired image according to an exemplary embodiment. Referring to Fig. 2, Fig. 2 graphically depicts an overview of a line-discovery procedure 200 in accordance with an exemplary embodiment. This procedure 200 consists of two main parts. The input image 210 is provided to the processor. As shown, this image includes a pair of intersecting edges 212 and 214 . These intersecting edges may represent corner regions of the object 150 described above. An edge point extractor 220 processes the input image 210 to obtain a set 230 of candidate edge points including edge points 232 and 234 present along edges 212 and 214, respectively. Edge points 232 , 234 and their associated data (eg, intensity gradient information described below) are provided to a recursive line finder 240 , which provides information about the selected edge points. It performs a series of iterative processes. The goal of the iterative process is to attempt to fit other found edge points to candidate line features. As a result of performing the line-discovery process 240, lines 252 and 254 are found as shown. These results may be provided to other downstream processes 260 that use the information - eg, alignment processes, robotic manipulations, inspections, ID readings, part/surface inspections, and the like.

Referring to FIG. 3 , FIG. 3 describes a procedure for extracting edge points according to an embodiment. One or more images including objects or surfaces having edge features to be found in the scene are acquired (step 310). These image(s) may be extracted by a single camera or multiple cameras. In either case, the image pixels may be (optionally) transformed into a new and/or common coordinate space with appropriate calibration parameters in step 320 . This step may further include smoothing the image as described below. In certain embodiments, when multiple cameras are imaging discrete regions of a scene - for example, focusing on a corner region of a larger object - the common coordinate space is an empty region between the camera's fields of view. can be considered. As described below, lines extending between these fields of view (eg, an object edge connecting two found corner regions) may be extrapolated by the system and method of an exemplary embodiment. The edge points required to find the lines are extracted from the image(s) in the appropriate coordinate space by an edge point extractor using gradient field projection in step 330 . Gradient values are first computed for each pixel, resulting in two images for the x and y gradient components. These image(s) are further processed by projecting a gradient field over many caliper-like zones. Unlike conventional caliper tools that project intensity values, by projecting a gradient field according to this embodiment, the gradient orientation can be preserved, which facilitates the process of finding subsequent lines as described below. do.

Referring also to the diagram of FIG. 4 at step 340 , the portion of the image containing the candidate edge features (caliper-like region) 400 is a gradient field (represented by a plurality of projections 410 , 420 , 430 ). Subject to a projection and searched over the (approximately) expected orientation of the edges in the search direction (arrow SD), the projection repeats over region 400 in the orthogonal projection direction (arrow PD). The edges in each projection (eg projection 420 ) are seen as local maxima in the gradient field 440 associated with that projection. In general, in the projection associated with an edge, a series of edge points exhibits an intensity gradient (vectors 552, 554) orthogonal to the direction of extension of this edge. As described below, the user can define the projection direction based on the expected line orientation. Alternatively, this may be provided by default or by other mechanisms - eg by analyzing features in the image.

Two particle size parameters are involved in the gradient projection step described above. Before calculating the gradient field, the user may choose to smooth the image using an isotropic Gaussian kernel. The first granularity determines the size of this Gaussian smoothing kernel. As shown in diagram 500 of FIG. 5 , image 210 is smoothed by applying appropriately sized Gaussian kernels (eg, large 512 , medium 514 , small 516 ). Thus, the first granularity parameter determines the size of the isotropic Gaussian smoothing kernel before calculating the gradient length.

After calculating the gradient field, a Gaussian-weighted projection is performed by this process, rather than the uniform weighting done in conventional caliper tools. Thus, the second granularity parameter is the size of the one-dimensional (1D) Gaussian kernel used during gradient field projection, as shown in FIG. to decide During normal operation, the user verifies (using the GUI) all extracted edges overlaid on the image, and then the number of extracted edges along the line to be discovered, avoiding an excessive number of edges due to background noise in the image Adjust the particle size and contrast thresholds until they look satisfactory. In other words, by this step the signal-to-noise ratio can be optimized for the image characteristics. This adjustment may be performed automatically by the system using default values in various embodiments. It is understood that using a Gaussian weighting function is one of several approaches to weighting the projection, including (eg) uniform weighting.

The overall flow of extracting and projecting the gradient field is graphically illustrated in diagram 700 of FIG. 7 . Two granularity parameters, an isotropic Gaussian kernel 710 and a 1D Gaussian kernel 720 , are respectively shown in each half of the overall diagram 700 . As shown, each acquired image 210 is subjected to smoothing and decimation 730 . The resulting image 740 is subjected to a gradient field calculation 750 as described above, resulting in two gradient images 752 and 754 . These gradient images are also represented by g _x and g _y representing two orthogonal axes in a common coordinate space. In addition to the two gradient images, the intensity image 756 is also generally (1D Gaussian kernel 720 ) and subjected to a smoothing, decimation and projection process 760 (using a Gaussian-weighted projection 770 ) based on the The result is a projection profile of gradient image 772 (g _x ), image 774 (g _y ), and intensity image 776 .

Referring also to step 350 in procedure 300 (FIG. 3), qualified edge points are extracted by combining the 1D projection profiles of the x and y gradient images. This is accomplished using compute 780 the raw contrast and compute 790 normalized contrast based on the intensity image. More specifically, any local peak with a raw projected gradient size and a normalized projected gradient size that exceeds each threshold is considered as a candidate edge point for finding a subsequent line according to the following exemplary equation:

(g _x ² + g _y ² ) ^1/2 > T _ABS

(g _x ² + g _y ² ) ^1/2 /I > T _NORM

where g _x and g _y are the values of the x-gradient and y-gradient projections, respectively, at the pixel location, I is the intensity, T _ABS is the absolute contrast threshold for the raw projected gradient size, and T _NORM is the intensity - Normalized contrast threshold for the normalized projected gradient size.

In particular, when both the absolute and normalized contrasts of a point exceed the respective thresholds, only this point is considered as a candidate edge point. This is shown as upper right quadrant 810 in the exemplary graph 800 of normalized contrast threshold (T _NORM ) versus absolute contrast threshold (T _ABS ). The use of dual thresholds (absolute and normalized thresholds) is generally different from the conventional approach, which generally uses absolute contrast thresholds. The benefit of the dual contrast threshold is evident when, illustratively, the image contains both a dark intensity region and a bright intensity region containing edges of interest. In order to detect edges in dark areas of the image, it is desirable to set a low contrast threshold. However, this low contrast setting can detect false edges in bright parts of the image. Conversely, to avoid detecting false edges in bright areas of the image, it is desirable to set a high contrast threshold. However, at high contrast settings the system may not properly detect edges in dark areas of the image. By using a second normalized contrast threshold in addition to the traditional absolute contrast threshold, the system can properly detect edges in both dark and bright regions, and avoid detecting false edges in bright regions of the image. can Thus, through the use of dual contrast thresholds, it is possible to detect relevant edges while avoiding spurious edges, thereby maximizing the speed and robustness of the step of finding subsequent lines in the overall process. function to

Referring further to procedure step 350 (FIG. 3), once all edge points have been extracted, these edge points are represented and stored in a data structure convenient for subsequent line-finders to operate on. For example, the following tuple:

It is expressed as p = (x,y,gx,gy,gm,go,I,gm/I,m,n),

where (x,y) is the position of the edge point, (g _x ,g _y ) is the value of each x-gradient and y-gradient projection, and (g _m ,g _o ) is from (g _x ,g _y ) is the computed gradient size and orientation, I is the intensity at the edge point location, g _m /I is the intensity-normalized contrast obtained by dividing the gradient size (g _m ) by the intensity (I), m is is the image index, and n is the projection area index. As with standard caliper tools, the position of the edge points can be interpolated to improve accuracy.

It is generally understood that the process of extracting edge points operates to execute a gradient field projection in a single direction that substantially matches the expected line angle. Thus, the tool is most sensitive to edges at this angle, and the sensitivity drops off gradually at edges at other angles, where the rate of drop depends on the granularity setting, which indirectly determines the gradient projection length. As a result, this process is limited to finding lines that have an angle "near" the expected line angle, according to the angular range specified by the user. Although this process is adapted to find non-orthogonal lines, this process in various embodiments finds arbitrary angular lines over 360 degrees by performing projection in multiple directions, including orthogonal directions (omnidirectional lines). It is considered that it can be generalized to find

Referring now to step 360 in procedure 300 (FIG. 3), edge point candidates that exceed a threshold are provided to a line-finder in accordance with an exemplary embodiment. For example, the line-finder operates recursively and uses (eg) RANdom SAmple Concensus (RANSAC)-based technology. See also line-discovery procedure 900 in FIG. 9 . At step 910 , the user selects the expected line in the image along with (eg) the expected angle, angular tolerance, distance tolerance, and (exemplarily) the minimum coverage score (generally defined below) via the GUI. Specifies the maximum number of This parameter is used in the line-finder to run the next process. This line is found for each subregion of the image by running the RANSAC line finder recursively, and edge point outliers from one step become the input points for the next step. Accordingly, at step 920, procedure 900 selects a pair of edge points that are part of the group of edge points identified as outliers in the edge-discovery process. Procedure 900 attempts to fit the model line to selected edge points based on matching gradient values that match the model line (within the selected tolerance range). At step 924 , one or more line candidate(s) from step 922 are returned. Each line-discovery step returns a candidate line, its outliers and outliers. The returned line(s) are subjected to an operation on stationary edge points having positions and gradients that coincide with the line candidates (step 926). At step 928 , the candidate line with the maximum outlier count is identified. The line-discovery phase described above (steps 920-928) ends when the maximum number of allowed RANSAC iterations is reached (decision step 930). The maximum number of iterations within each line-finding phase is computed automatically using a user-specified assurance level and an internally computed worst-case ratio of outliers. Each line discovery step returns the line with the maximum number of captured edge points among all iterations, according to user-specified fit tolerances, geometric constraints and polarity. Each edge point can only be assigned to a list of normal values of a single line, and each line is allowed to contain at most one edge point from each projection zone. The gradient orientation of the edge point, along with its position, is used to determine whether the edge point should be included in the candidate line's intrinsic list. In particular, the edge points should have a gradient orientation consistent with the angle of the candidate line.

If decision step 930 determines that more iterations are allowed, then the outliers from the best outlier candidates are returned to the RANSAC process (step 920) for use in finding line candidates (step 940).

During each RANSAC iteration, two edge points belonging to different projection regions are randomly selected, and there may be a line that fits these two points. The resulting candidate line receives additional consideration only if the angle of the candidate line coincides with the draft angle of the two edges at the pair of points and if the angle of the line matches the user-specified uncertainty range. In general, the draft direction of the edge point is nominally orthogonal, but is allowed to differ by a user-configured angular tolerance. If the candidate line passes these initial tests, the number of stationary edge points is evaluated, and if not, a new RANSAC iteration is initiated. An edge point is considered a normal value of a candidate line only if its draft direction and location coincide with a line based on a user-specified draft angle and distance tolerance.

When the RANSAC iterations reach a maximum (decision step 930), the normal values of the best found line candidates obtain an improved line fit using (e.g., least squares regression) or other acceptable approximation technique. and repeat this step up to N times (eg, 3 or more) until the number of normal values does not increase or decrease further, to re-evaluate the set of stationary edge points (step 960). This is the line indicated as being found in step 970 .

Decision step 980 determines whether more lines are to be found (eg, based on searching for additional sub-regions or other criteria), and if so, the process returns to step 920, where a new Operate on the edge points of the set (step 982). If the points have been run across or the maximum iteration count has been reached, the procedure 900 returns at step 990 the set of (ie, multiple) found lines in the image.

The multi-line finder is adapted to finally adjust the existing result if two line results intersect each other in the inspection zone. 10 and 11, for closely spaced parallel lines 1010 and 1020, often erroneous line results (i.e., FIG. 10) may be obtained due to the statistical nature of the RANSAC procedure. . However, when such an error occurs, the correct line with a reduced-fit residual and a coverage score often increased by exchanging a group of points of normal value (arrow 1120 in group 1110 in FIG. 11 ) can be found Swapping points can be most effective when the image contains closely spaced parallel lines as shown. Conversely, when the image contains lines 1210 and 1220 that actually intersect each other as shown in FIGS. 12 and 13 , the coverage scores swap points (arrows within group 1240 in FIG. 12 ). If decremented after 1230), the original result obtained before exchanging is maintained to successfully detect intersecting lines by the process.

It is understood that the RANSAC procedure is only one of several techniques by which the line-finder can fit points into a line. In an alternative embodiment, candidate points may be selected according to a displacement established between these points, or the image may be processed using (eg) an exhaustive search technique. Accordingly, reference to a RANSAC technique as used herein should be interpreted broadly to include several similar point-fit techniques.

Additional functionality of these systems and methods may be provided. These features support mixed-polarity, automatically compute the projected area width, support multi-view line discovery, and eliminate optical distortion by removing pre-warpage from the input image. includes doing These functions are further described below.

14-16 , an exemplary embodiment line-discovery system and method provides a standard bright-to-dark polarity, dark-to-bright polarity, and standard bright-to-dark polarity for contrast between found edges, and Either polarity setting (each) is generally supported. Furthermore, this system and method may further support a mixed-polarity setup (FIG. 17) in which the bright-to-dark polarity and dark-to-bright polarity characteristics are both visible on the same line. The line-finding results of all four settings are shown in the following figure. In an exemplary embodiment, the systems and methods may include a mixed-polarity setup that may find a single line containing edge points of opposite polarity. This differs from the conventional setup where all edge points of a single line have either polarity - but only one polarity, "either". The mixed-polarity setting can be advantageous when used to analyze light and dark checkerboards of (eg) calibration plates, among other applications.

The user can select the improved shift invariance to find the line. In this case, the edge point extractor uses substantially overlapping projection regions to improve result stability. If the regions do not overlap, the pixels considered can potentially shift out of the projection region when the image is shifted, resulting in poor shift invariance in the line-finding result. The overlapping projection regions ensure that the pixels under consideration are continuously covered by the projection regions. When overlapping projection zones are used, incremental computations can be performed to maintain speed with as low a level of optimization as possible.

The user may provide a mask that omits certain portions of the imaged surface and/or images obtained from analysis of line features. This may be desirable if the surface contains known line features of no interest (eg, barcodes that are analyzed by text, text, and any other structure, other mechanisms unrelated to the operation in which the lines are found). Thus, the edge point extractor may support image masking in which “don't care” regions in the image may be masked out, and “interest” regions may be masked in. When such masking occurs, the coverage scores of the found lines are illustratively re-weighted according to the number of edge points in the mask.

Referring to the exemplary image region 1800 of FIG. 18 , FIG. 18 illustrates coverage scores when image masks are present and the effect of image masking on these coverage scores. The edge point extractor supports image masking where "regions of interest" in the image can be masked out. As shown, the found line 1810 is characterized as edge points of interest (based on the “interest” mask region 1820 ). These edge-of-interest points consist of an edge-of-interest outlier 1830 to line 1810 and an edge-of-interest outlier 1840 to line 1810 . Uninterested edge points 1850 on line 1810 exist between regions of interest 1820 of the mask as shown in this example, and the coverage score is computed even if these uninterested edge points are normally present on the line. not included in A potential location 1860 of the edge points along line 1810 is also determined as shown. This potential location is located between known points with a predictable spacing based on the spacing of the points found. Illustratively, the coverage scores of the found lines are reweighted according to the number of edge points in the mask. So the coverage score is changed to:

Coverage score = number of edge-of-interest outliers for a line/(number of edge-of-interest outliers for a line + edge-of-interest outliers for a line + number of potential positions of interest on edges).

After executing the line-discovery process according to the systems and methods herein, the found lines may be classified in several ways based on classification criteria specified by the user (eg (via a GUI)). The user may select from intrinsic classification measures such as normal coverage score, intensity or contrast. Users can also choose from extrinsic classification measures such as signed distance or relative angle. When using the extrinsic classification action, the user can specify a reference line segment from which to compute the extrinsic measure of the found lines.

As generally noted above, the systems and methods may include Multi-Field-of-View (MFOV) overloads that may pass image vectors from different fields of view to the process. The images should all be in a common client coordinate space based on the calibration. As mentioned above, this functionality can be extremely advantageous in application scenarios where multiple cameras are used to capture partial regions of a single part. Because edge points retain gradient information, line features projected between gaps in the field of view (when gradients in both FOVs match a given line orientation and alignment in each FOV) can still be analyzed.

In particular, this system and method does not require (ie, does not require) distortion to be removed (in the image) in order to remove non-linear distortion, assuming the distortion is not severe. If the image is not warped, the system and method can still detect candidate edge points and map the point's position and gradient vector through a non-linear transformation.

It is evident that the line-finder provided in accordance with this system and method and several alternative embodiments/improvements is an effective and powerful tool for determining multiple line features under different conditions. In general, these systems and methods have no particular limitation on the maximum number of lines found in an image when used to discover line features. Only memory and computation time put a practical limit on the number of lines that can be discovered.

The above is a detailed description of an exemplary embodiment of the present invention. Various modifications and additions may be made without departing from the spirit and scope of the present invention. Features of each of the various embodiments described above can be combined with features of other described embodiments, where appropriate, to provide multiple feature combinations in associated new embodiments. Furthermore, while the foregoing describes a number of distinct embodiments of the apparatus and method of the present invention, what has been described herein is merely illustrative of the application of the principles of the present invention. For example, as used herein, the terms “process” and/or “processor” should be interpreted broadly to include various electronic hardware and/or software-based functions and components (and alternatively, functional “modules”). " or "an element"). Furthermore, the illustrated process or processor may be combined with other processes and/or processors or divided into several sub-processes or processors. Such sub-processors and/or sub-processors may be combined in various ways according to the embodiments disclosed herein. Further, it is expressly stated herein that any function, process, and/or processor may be implemented using electronic hardware, software consisting of a non-transitory computer-readable medium of program instructions, or a combination of hardware and software. are considered Additionally, as used herein, "vertical", "horizontal", "up", "down", "lower", "upper", "side", "front", "rear", "left", Various orientation and orientation terms, such as "right", are used only as relative conventions and are not used as absolute orientations/positions with respect to a fixed coordinate space, such as the direction of action of gravity. Additionally, the terms "substantially" or "approximately," when used for a given measurement, value, or characteristic, refer to an amount that is within the normal operating range that will achieve the desired result, although this is not necessarily due to the internal inaccuracies of the system and the tolerance of the system. Includes some variation due to within-tolerance error (eg, 1-5 percent). Accordingly, this description should be construed as illustrative only and not intended to limit the scope of the present invention.

Claims (1)

A system for finding line features in an acquired image, comprising:
a vision system processor receiving image data of a scene comprising line features and having an edge point extractor; and
including a line-finder;
The edge point extractor is:
(a) applying the acquired image to a gradient field calculation process to generate two gradient component images and an intensity image;
(b) applying a weighted projection to the two gradient component images and the intensity image to produce one-dimensional (1D) projection profiles of the two gradient component images and a projective image;
(c) extracting candidate edge points by combining the 1D projection profiles of the two gradient component images;
and the line-finder generates a plurality of lines consistent with the extracted edge points.

Images