{
  "id": "enwiki-001375290702",
  "slug": "corner-detection",
  "title": "Corner detection",
  "qid": "",
  "lead": "using corner detection Corner detection is an approach used within computer vision systems to extract certain kinds of features and infer the contents of an image. Corner detection is frequently used in motion detection, image registration, video tracking, image mosaicing, panorama stitching, 3D reconstruction and object recognition. Corner detection overlaps with the topic of interest point detection.",
  "body": "using corner detection]] Corner detection is an approach used within computer vision systems to extract certain kinds of features and infer the contents of an image. Corner detection is frequently used in motion detection, image registration, video tracking, image mosaicing, panorama stitching, 3D reconstruction and object recognition. Corner detection overlaps with the topic of interest point detection. == The Harris & Stephens / Shi–Tomasi corner detection algorithms == Harris and Stephens improved upon Moravec's corner detector by considering the differential of the corner score with respect to direction directly, instead of using shifted patches. (This corner score is often referred to as autocorrelation, since the term is used in the paper in which this detector is described. However, the mathematics in the paper clearly indicate that the sum of squared differences is used.) Without loss of generality, we will assume a grayscale 2-dimensional image is used. Let this image be given by I . Consider taking an image patch over the area (u, v) and shifting it by (x, y) . The weighted sum of squared differences (SSD) between these two patches, denoted S , is given by S(x, y) = \\sum_u \\sum_v w(u, v) [I(u + x, v + y) - I(u, v)]^2. I(u + x, v + y) can be approximated by a Taylor expansion. Let I_x and I_y be the partial derivatives of I , such that I(u + x, v + y) \\approx I(u, v) + I_x(u, v) x + I_y(u, v) y. This produces the approximation S(x, y) \\approx \\sum_u \\sum_v w(u, v) [I_x(u, v) x + I_y(u, v) y]^2, which can be written in matrix form: S(x, y) \\approx \\begin{bmatrix} x & y \\end{bmatrix} A \\begin{bmatrix} x \\\\ y \\end{bmatrix}, where A is the structure tensor, A = \\sum_u \\sum_v w(u, v) \\begin{bmatrix} I_x(u, v)^2 & I_x(u, v) I_y(u, v) \\\\ I_x(u, v) I_y(u,v) & I_y(u, v)^2 \\end{bmatrix} = \\begin{bmatrix} \\langle I_x^2 \\rangle & \\langle I_x I_y \\rangle \\\\ \\langle I_x I_y \\rangle & \\langle I_y^2 \\rangle \\end{bmatrix}. In words, we find the covariance of the partial derivative of the image intensity I with respect to the x and y axes. Angle brackets denote averaging (i.e. summation over (u, v) ), and w(u, v) denotes the type of window that slides over the image. If a box filter is used, the response will be anisotropic, but if a Gaussian is used, then the response will be isotropic. A corner (or in general an interest point) is characterized by a large variation of S in all directions of the vector \\begin{bmatrix} x & y \\end{bmatrix} . By analyzing the eigenvalues of A , this characterization can be expressed in the following way: A should have two \"large\" eigenvalues for an interest point. Based on the magnitudes of the eigenvalues, the following inferences can be made based on this argument: If \\lambda_1 \\approx 0 and \\lambda_2 \\approx 0, then this pixel (x, y) has no features of interest. If \\lambda_1 \\approx 0 and \\lambda_2 has some large positive value, then an edge is found. If \\lambda_1 and \\lambda_2 have large positive values, then a corner is found. Harris and Stephens note that exact computation of the eigenvalues is computationally expensive, since it requires the computation of a square root, and instead suggest the function M_c = \\lambda_1 \\lambda_2 - \\kappa (\\lambda_1 + \\lambda_2)^2 = \\det(A) - \\kappa \\operatorname{tr}^2(A), where \\kappa is a tunable sensitivity parameter. Therefore, the algorithm does not have to actually compute the eigenvalue decomposition of the matrix A, and instead it is sufficient to evaluate the determinant and trace of A to find corners, or rather interest points in general. The Shi–Tomasi corner detector directly computes \\min(\\lambda_1, \\lambda_2) because under certain assumptions, the corners are more stable for tracking. Note that this method is also sometimes referred to as the Kanade–Tomasi corner detector. The value of \\kappa has to be determined empirically, and in the literature values in the range 0.04–0.15 have been reported as feasible. One can avoid setting the parameter \\kappa by using Noble's corner measure M_c' which amounts to the harmonic mean of the eigenvalues: M_c' = 2 \\frac{\\det(A)}{\\operatorname{tr}(A) + \\epsilon}, where \\epsilon is a small positive constant. If A can be interpreted as the precision matrix for the corner position, the covariance matrix for the corner position is A^{-1} , i.e. \\frac{1}{\\langle I_x^2 \\rangle \\langle I_y^2 \\rangle - \\langle I_x I_y \\rangle^2} \\begin{bmatrix} \\langle I_y^2 \\rangle & -\\langle I_x I_y \\rangle \\\\ -\\langle I_x I_y \\rangle & \\langle I_x^2 \\rangle \\end{bmatrix}. The sum of the eigenvalues of A^{-1} , which in that case can be interpreted as a generalized variance (or a \"total uncertainty\") of the corner position, is related to Noble's corner measure M_c' as \\lambda_1(A^{-1}) + \\lambda_2(A^{-1}) = \\frac{\\operatorname{tr}(A)}{\\det(A)} \\approx \\frac{2}{M_c'}. T_\\mathbf{x'}(\\mathbf x) = \\nabla I(\\mathbf{x'})^{\\top}(\\mathbf{x}-\\mathbf{x'}) = 0 where \\nabla I(\\mathbf{x'}) = \\begin{bmatrix} I_{\\mathbf{x}} & I_{\\mathbf{y}} \\end{bmatrix}^{\\top} is the gradient vector of the image I at \\mathbf{x'} . The point \\mathbf{x}_{0} closest to all the tangent lines in the window N is: \\mathbf{x}_{0}=\\underset{\\mathbf{x}\\in \\mathbb{R}^{2\\times 1}}{\\operatorname{argmin}}\\int_{\\mathbf{x'}\\in N}T_{\\mathbf{x'}}(\\mathbf{x})^{2}d\\mathbf{x'} The distance from \\mathbf{x}_{0} to the tangent lines T_{\\mathbf{x'}} is weighted by the gradient magnitude, thus giving more importance to tangents passing through pixels with strong gradients. Solving for \\mathbf{x}_{0} : \\begin{align} \\mathbf{x}_{0}&=\\underset{\\mathbf{x}\\in \\mathbb{R}^{2\\times 1}}{\\operatorname{argmin}} \\int_{\\mathbf{x'}\\in N} \\left(\\nabla I\\left(\\mathbf{x'}\\right)^{\\top} \\left(\\mathbf{x}-\\mathbf{x'}\\right)\\right)^{2} d\\mathbf{x'}\\\\ &=\\underset{\\mathbf{x}\\in \\mathbb{R}^{2\\times 1}}{\\operatorname{argmin}}\\int_{\\mathbf{x'}\\in N}(\\mathbf{x}-\\mathbf{x'})^{\\top}\\nabla I(\\mathbf{x'})\\nabla I(\\mathbf{x'})^{\\top}(\\mathbf{x}-\\mathbf{x'})d\\mathbf{x'}\\\\ &=\\underset{\\mathbf{x}\\in \\mathbb{R}^{2\\times 1}}{\\operatorname{argmin}} \\left(\\mathbf{x}^{\\top}A\\mathbf{x}-2\\mathbf{x}^{\\top}\\mathbf{b}+c\\right) \\end{align} A\\in\\mathbb{R}^{2\\times 2},\\textbf{b}\\in\\mathbb{R}^{2\\times 1},c\\in\\mathbb{R} are defined as: \\begin{align} A&=\\int \\nabla I(\\mathbf{x'})\\nabla I(\\mathbf{x'})^{\\top}d\\mathbf{x'}\\\\ \\mathbf{b}&=\\int \\nabla I(\\mathbf{x'})\\nabla I(\\mathbf{x'})^{\\top}\\mathbf{x'}d\\mathbf{x'}\\\\ c&=\\int \\mathbf{x'}^{\\top}\\nabla I(\\mathbf{x'})\\nabla I(\\mathbf{x'})^{\\top}\\mathbf{x'}d\\mathbf{x'}\\\\ \\end{align} Minimizing this equation can be done by differentiating with respect to x and setting it equal to 0: 2A\\mathbf{x}-2\\mathbf{b}=0 \\Rightarrow A\\mathbf{x}=\\mathbf{b} Note that A\\in\\mathbb{R}^{2\\times 2} is the structure tensor. For the equation to have a solution, A must be invertible, which implies that A must be full rank (rank 2). Thus, the solution x_{0}=A^{-1}\\mathbf{b} only exists where an actual corner exists in the window N . A methodology for performing automatic scale selection for this corner localization method has been presented by Lindeberg by minimizing the normalized residual \\tilde{d}_{\\min} = \\frac{c - b^T A^{-1} b}{\\operatorname{trace} A} over scales. Thereby, the method has the ability to automatically adapt the scale levels for computing the image gradients to the noise level in the image data, by choosing coarser scale levels for noisy image data and finer scale levels for near ideal corner-like structures. Notes: c can be viewed as a residual in the least-square solution computation: if c=0 , then there was no error. this algorithm can be modified to compute centers of circular features by changing tangent lines to normal lines. g(x, y, t) = \\frac {1}{2{\\pi} t} e^{-\\left(x^2+y^2\\right)/2t} with local scale parameter t : L(x, y, t)\\ = g(x, y, t) * I(x, y) and let L_x = \\partial_x L and L_y = \\partial_y L denote the partial derivatives of L . Moreover, introduce a Gaussian window function g(x, y, s) with integration scale parameter s . Then, the multi-scale second-moment matrix can be defined as \\mu(x, y; t, s) = \\int_{\\xi = -\\infty}^{\\infty} \\int_{\\eta = -\\infty}^{\\infty} \\begin{bmatrix} L_x^2(x-\\xi, y-\\eta; t) & L_x(x-\\xi, y-\\eta; t) \\, L_y(x-\\xi, y-\\eta; t) \\\\ L_x(x-\\xi, y-\\eta; t) \\, L_y(x-\\xi, y-\\eta; t) & L_y^2(x-\\xi, y-\\eta; t) \\end{bmatrix} g(\\xi, \\eta; s) \\, d\\xi \\, d\\eta. Then, we can compute eigenvalues of \\mu in a similar way as the eigenvalues of A and define the multi-scale Harris corner measure as M_c(x, y; t, s) = \\det (\\mu(x, y; t, s)) - \\kappa \\, \\operatorname{trace}^2(\\mu(x, y; t, s)) . Concerning the choice of the local scale parameter t and the integration scale parameter s , these scale parameters are usually coupled by a relative integration scale parameter \\gamma such that s = \\gamma^2 t , where \\gamma is usually chosen in the interval [1, 2] . Thus, we can compute the multi-scale Harris corner measure M_c(x, y; t, \\gamma^2 t) at any scale t in scale-space to obtain a multi-scale corner detector, which responds to corner structures of varying sizes in the image domain. In practice, this multi-scale corner detector is often complemented by a scale selection step, where the scale-normalized Laplacian operator \\nabla^2_\\mathrm{norm} L(x, y; t)\\ = t \\nabla^2 L(x, y, t) = t (L_{xx}(x, y, t) + L_{yy}(x, y, t)) is computed at every scale in scale-space and scale adapted corner points with automatic scale selection (the \"Harris-Laplace operator\") are computed from the points that are simultaneously: spatial maxima of the multi-scale corner measure M_c(x, y; t, \\gamma^2 t) (\\hat{x}, \\hat{y}; t) = \\operatorname{argmaxlocal}_{(x, y)} M_c \\left(x, y; t, \\gamma^2 t\\right) local maxima or minima over scales of the scale-normalized Laplacian operator \\nabla^2_\\mathrm{norm}(x, y, t) : \\hat{t} = \\operatorname{argmaxminlocal}_{t} \\nabla^2_\\mathrm{norm}L(\\hat{x}, \\hat{y}; t) \\tilde{\\kappa}(x, y;t) = L_x^2 L_{yy} + L_y^2 L_{xx} - 2 L_x L_y L_{xy} and to detect positive maxima and negative minima of this differential expression at some scale t in the scale space representation L of the original image. A main problem when computing the rescaled level curve curvature entity at a single scale however, is that it may be sensitive to noise and to the choice of the scale level. A better method is to compute the \\gamma -normalized rescaled level curve curvature \\tilde{\\kappa}_\\mathrm{norm}(x, y;t) = t^{2 \\gamma} (L_x^2 L_{yy} + L_y^2 L_{xx} - 2 L_x L_y L_{xy}) with \\gamma = 7/8 and to detect signed scale-space extrema of this expression, that are points and scales that are positive maxima and negative minima with respect to both space and scale (\\hat{x}, \\hat{y}; \\hat{t}) = \\operatorname{argminmaxlocal}_{(x, y; t)} \\tilde{\\kappa}_\\mathrm{norm}(x, y; t) in combination with a complementary localization step to handle the increase in localization error at coarser scales. In this way, larger scale values will be associated with rounded corners of large spatial extent while smaller scale values will be associated with sharp corners with small spatial extent. This approach is the first corner detector with automatic scale selection (prior to the \"Harris-Laplace operator\" above) and has been used for tracking corners under large scale variations in the image domain and for matching corner responses to edges to compute structural image features for geon-based object recognition. (\\hat{x}, \\hat{y}; \\hat{t}) = \\operatorname{argminmaxlocal}_{(x, y; t)} (D_\\mathrm{norm} L)(x, y; t) where D_{norm} L denotes the appropriate scale-normalized differential entity (defined below). These detectors are more completely described in blob detection. The scale-normalized Laplacian of the Gaussian and difference-of-Gaussian features (Lindeberg 1994, 1998; Lowe 2004) \\begin{align} \\nabla^2_\\mathrm{norm} L(x, y; t) & = t \\, (L_{xx} + L_{yy})\\\\ &\\approx \\frac{t \\left( L(x, y; t+\\Delta t) - L(x, y; t) \\right)}{\\Delta t} \\end{align} do not necessarily make highly selective features, since these operators may also lead to responses near edges. To improve the corner detection ability of the differences of Gaussians detector, the feature detector used in the SIFT system therefore uses an additional post-processing stage, where the eigenvalues of the Hessian of the image at the detection scale are examined in a similar way as in the Harris operator. If the ratio of the eigenvalues is too high, then the local image is regarded as too edge-like, so the feature is rejected. Also Lindeberg's Laplacian of the Gaussian feature detector can be defined to comprise complementary thresholding on a complementary differential invariant to suppress responses near edges. The scale-normalized determinant of the Hessian operator (Lindeberg 1994, 1998) \\det H_\\mathrm{norm} L = t^2 (L_{xx} L_{yy} - L_{xy}^2) is on the other hand highly selective to well localized image features and does only respond when there are significant grey-level variations in two image directions and is in this and other respects a better interest point detector than the Laplacian of the Gaussian. The determinant of the Hessian is an affine covariant differential expression and has better scale selection properties under affine image transformations than the Laplacian operator (Lindeberg 2013, 2015). Experimentally this implies that determinant of the Hessian interest points have better repeatability properties under local image deformation than Laplacian interest points, which in turns leads to better performance of image-based matching in terms higher efficiency scores and lower 1&minus;precision scores. The scale selection properties, affine transformation properties and experimental properties of these and other scale-space interest point detectors are analyzed in detail in (Lindeberg 2013, 2015). (H f') = A^{-T} \\, (H f) \\, A^{-1} , \\mu' = A^{-T} \\, \\mu \\, A^{-1} , Lindeberg (2013, 2015) proposed to define four feature strength measures from the Hessian matrix in related ways as the Harris and Shi-and-Tomasi operators are defined from the structure tensor (second-moment matrix). Specifically, he defined the following unsigned and signed Hessian feature strength measures: the unsigned Hessian feature strength measure I: D_{1,\\mathrm{norm}} L = \\begin{cases} t^2 \\, (\\det H L - k \\, \\operatorname{trace}^2 H L) & \\mbox{if} \\, \\det H L - k \\, \\operatorname{trace}^2 H L > 0 \\\\ 0 & \\mbox{otherwise} \\end{cases} the signed Hessian feature strength measure I: \\tilde{D}_{1,\\mathrm{norm}} L = \\begin{cases} t^2 \\, (\\det H L - k \\, \\operatorname{trace}^2 H L) & \\mbox{if} \\, \\det H L - k \\, \\operatorname{trace}^2 H L > 0 \\\\ t^2 \\, (\\det H L + k \\, \\operatorname{trace}^2 H L) & \\mbox{if} \\, \\det H L + k \\, \\operatorname{trace}^2 H L the unsigned Hessian feature strength measure II: D_{2,\\mathrm{norm}} L = t \\, \\min(|\\lambda_1(H L)|, |\\lambda_2(H L)|) the signed Hessian feature strength measure II: \\tilde{D}_{2,\\mathrm{norm}} L = \\begin{cases} t \\, \\lambda_1(H L) & \\mbox{if} \\, |\\lambda_1(H L)| where \\operatorname{trace} H L = L_{xx} + L_{yy} and \\det H L = L_{xx} L_{yy} - L_{xy}^2 denote the trace and the determinant of the Hessian matrix H L of the scale-space representation L at any scale t , whereas \\lambda_1(H L) = L_{pp} = \\frac{1}{2} \\left( L_{xx}+L_{yy} - \\sqrt{(L_{xx}-L_{yy})^2 + 4 L_{xy}^2} \\right) \\lambda_2(H L) = L_{qq} = \\frac{1}{2} \\left( L_{xx}+L_{yy} + \\sqrt{(L_{xx}-L_{yy})^2 + 4 L_{xy}^2} \\right) denote the eigenvalues of the Hessian matrix. The unsigned Hessian feature strength measure D_{1,\\mathrm{norm}} L responds to local extrema by positive values and is not sensitive to saddle points, whereas the signed Hessian feature strength measure \\tilde{D}_{1,\\mathrm{norm}} L does additionally respond to saddle points by negative values. The unsigned Hessian feature strength measure D_{2,\\mathrm{norm}} L is insensitive to the local polarity of the signal, whereas the signed Hessian feature strength measure \\tilde{D}_{2,\\mathrm{norm}} L responds to the local polarity of the signal by the sign of its output. In Lindeberg (2015) these four differential entities were combined with local scale selection based on either scale-space extrema detection (\\hat{x}, \\hat{y}; \\hat{t}) = \\operatorname{argminmaxlocal}_{(x, y; t)} (D_\\mathrm{norm} L)(x, y; t) or scale linking. Furthermore, the signed and unsigned Hessian feature strength measures D_{2,\\mathrm{norm}} L and \\tilde{D}_{2,\\mathrm{norm}} L were combined with complementary thresholding on D_{1,\\mathrm{norm}} L > 0 . By experiments on image matching under scaling transformations on a poster dataset with 12 posters with multi-view matching over scaling transformations up to a scaling factor of 6 and viewing direction variations up to a slant angle of 45 degrees with local image descriptors defined from reformulations of the pure image descriptors in the SIFT and SURF operators to image measurements in terms of Gaussian derivative operators (Gauss-SIFT and Gauss-SURF) instead of original SIFT as defined from an image pyramid or original SURF as defined from Haar wavelets, it was shown that scale-space interest point detection based on the unsigned Hessian feature strength measure D_{1,\\mathrm{norm}} L allowed for the best performance and better performance than scale-space interest points obtained from the determinant of the Hessian \\det H_\\mathrm{norm} L = t^2 \\left(L_{xx} L_{yy} - L_{xy}^2\\right) . Both the unsigned Hessian feature strength measure D_{1,\\mathrm{norm}} L , the signed Hessian feature strength measure \\tilde{D}_{1,norm} L and the determinant of the Hessian \\det H_{norm} L allowed for better performance than the Laplacian of the Gaussian \\nabla_\\mathrm{norm}^2 L = t \\, (L_{xx} + L_{yy}) . When combined with scale linking and complementary thresholding on D_{1,\\mathrm{norm}} L > 0 , the signed Hessian feature strength measure \\tilde{D}_{2,\\mathrm{norm}} L did additionally allow for better performance than the Laplacian of the Gaussian \\nabla_{\\mathrm{norm}}^2 L . Furthermore, it was shown that all these differential scale-space interest point detectors defined from the Hessian matrix allow for the detection of a larger number of interest points and better matching performance compared to the Harris and Shi-and-Tomasi operators defined from the structure tensor (second-moment matrix). A theoretical analysis of the scale selection properties of these four Hessian feature strength measures and other differential entities for detecting scale-space interest points, including the Laplacian of the Gaussian and the determinant of the Hessian, is given in Lindeberg (2013) and an analysis of their affine transformation properties as well as experimental properties in Lindeberg (2015). C = \\left(\\frac{\\delta^2 I}{\\delta \\mathbf{t}^2}\\right)^2 - c|\\nabla I|^2, where \\bf{t} is the unit vector perpendicular to the gradient, and c determines how edge-phobic the detector is. The authors also note that smoothing (Gaussian is suggested) is required to reduce noise. Smoothing also causes displacement of corners, so the authors derive an expression for the displacement of a 90 degree corner, and apply this as a correction factor to the detected corners. c(\\vec{m}) = e^{-\\left(\\frac{I(\\vec{m}) - I(\\vec{m}_0)}{t}\\right)^6} where t is the brightness difference threshold, I is the brightness of the pixel and the power of the exponent has been determined empirically. This function has the appearance of a smoothed top-hat or rectangular function. The area of the SUSAN is given by: n(M) = \\sum_{\\vec{m}\\in M} c(\\vec{m}) If c is the rectangular function, then n is the number of pixels in the mask which are within t of the nucleus. The response of the SUSAN operator is given by: R(M) = \\begin{cases} g - n(M) & \\mbox{if}\\ n(M) where g is named the 'geometric threshold'. In other words, the SUSAN operator only has a positive score if the area is small enough. The smallest SUSAN locally can be found using non-maximal suppression, and this is the complete SUSAN operator. The value t determines how similar points have to be to the nucleus before they are considered to be part of the univalue segment. The value of g determines the minimum size of the univalue segment. If g is large enough, then this becomes an edge detector. For corner detection, two further steps are used. Firstly, the centroid of the SUSAN is found. A proper corner will have the centroid far from the nucleus. The second step insists that all points on the line from the nucleus through the centroid out to the edge of the mask are in the SUSAN. ==The Trajkovic and Hedley corner detector== In a manner similar to SUSAN, this detector directly tests whether a patch under a pixel is self-similar by examining nearby pixels. \\vec{c} is the pixel to be considered, and \\vec{p} \\in P is point on a circle P centered around \\vec{c} . The point \\vec{p}' is the point opposite to \\vec{p} along the diameter. The response function is defined as: r(\\vec{c}) = \\min_{\\vec{p} \\in P} \\left(\\left(I(\\vec{p}) - I(\\vec{c})\\right)^2 + \\left(I(\\vec{p}') - I(\\vec{c})\\right) ^2\\right) This will be large when there is no direction in which the centre pixel is similar to two nearby pixels along a diameter. P is a discretised circle (a Bresenham circle), so interpolation is used for intermediate diameters to give a more isotropic response. Since any computation gives an upper bound on the \\min , the horizontal and vertical directions are checked first to see if it is worth proceeding with the complete computation of c . A = \\sum_u \\sum_v \\sum_w h(u,v, w) \\begin{bmatrix} L_x(u,v,w)^2 & L_x(u,v,w) L_y(u,v,w) & L_x(u,v,w) L_t(u,v,w) \\\\ L_x(u,v,w) L_y(u,v,w) & L_y(u,v,w)^2 & L_y(u,v,w) L_t(u,v,w) \\\\ L_x(u,v,w) L_t(u,v,w) & L_y(u,v,w) L_t(u,v,w) & L_t(u,v,w)^2 \\\\ \\end{bmatrix} = \\, s^{2 \\gamma_s} \\tau^{\\gamma_{\\tau}} \\left( L_{xx} L_{yy} L_{tt} + 2 L_{xy} L_{xt} L_{yt} - L_{xx} L_{yt}^2 - L_{yy} L_{xt}^2 - L_{tt} L_{xy}^2 \\right). In the work by Willems et al, a simpler expression corresponding to \\gamma_s = 1 and \\gamma_{\\tau} = 1 was used. In Lindeberg, it was shown that \\gamma_s = 5/4 and \\gamma_{\\tau} = 5/4 implies better scale selection properties in the sense that the selected scale levels obtained from a spatio-temporal Gaussian blob with spatial extent s = s_0 and temporal extent \\tau = \\tau_0 will perfectly match the spatial extent and the temporal duration of the blob, with scale selection performed by detecting spatio-temporal scale-space extrema of the differential expression. The Laplacian operator has been extended to spatio-temporal video data by Lindeberg, leading to the following two spatio-temporal operators, which also constitute models of receptive fields of non-lagged vs. lagged neurons in the LGN: \\partial_{t,\\mathrm{norm}} (\\nabla_{(x,y),\\mathrm{norm}}^2 L) = s^{\\gamma_s} \\tau^{\\gamma_{\\tau}/2} (L_{xxt} + L_{yyt}), \\partial_{tt,\\mathrm{norm}} (\\nabla_{(x,y),\\mathrm{norm}}^2 L) = s^{\\gamma_s} \\tau^{\\gamma_{\\tau}} (L_{xxtt} + L_{yytt}). For the first operator, scale selection properties call for using \\gamma_s = 1 and \\gamma_{\\tau} = 1/2 , if we want this operator to assume its maximum value over spatio-temporal scales at a spatio-temporal scale level reflecting the spatial extent and the temporal duration of an onset Gaussian blob. For the second operator, scale selection properties call for using \\gamma_s = 1 and \\gamma_{\\tau} = 3/4 , if we want this operator to assume its maximum value over spatio-temporal scales at a spatio-temporal scale level reflecting the spatial extent and the temporal duration of a blinking Gaussian blob. Colour extensions of spatio-temporal interest point detectors have been investigated by Everts et al. Online Implementation of the Harris Corner Detector - IPOL ==External links== Brostow, \"Corner Detection -- UCL Computer Science\"",
  "categories": [
    "10639558",
    "130042203",
    "23034719",
    "23603337",
    "24623845",
    "26220375",
    "7692542"
  ],
  "license": "CC BY-SA 4.0",
  "source_uri": "https://en.wikipedia.org/w/index.php?oldid=1375290702",
  "content_hash": "",
  "created_at": null,
  "updated_at": 1789594468.0,
  "claims": [],
  "contradictions": [],
  "confidence": 0.6,
  "csl": {
    "id": "enwiki-001375290702",
    "type": "webpage",
    "title": "Corner detection",
    "author": [
      {
        "family": "Anticloud FZ LLE",
        "literal": "Anticloud FZ LLE"
      }
    ],
    "container-title": "encyclopegia.org",
    "publisher": "Anticloud FZ LLE",
    "publisher-place": "Dubai, United Arab Emirates",
    "URL": "https://encyclopegia.org/a/corner-detection",
    "issued": {
      "date-parts": [
        [
          2026,
          11,
          16
        ]
      ]
    },
    "accessed": {
      "date-parts": [
        [
          2026,
          11,
          16
        ]
      ]
    },
    "license": "CC BY-SA 4.0",
    "DOI": "eo1:enwiki-001375290702",
    "isBasedOn": "https://en.wikipedia.org/w/index.php?oldid=1375290702",
    "note": "Immutable snapshot enwiki-001375290702"
  }
}