Skip to content

pix_opencv

Contributors

People who contribute to this project.

Objects

  • pix_opencv_athreshold pix_opencv_athreshold performs adaptive thresholding to segment an image, calculating a threshold individually for each pixel and assigning thresholded pixels a configurable maximum value (255 by default).
  • pix_opencv_backgroundsubtractor pix_opencv_backgroundsubtractor performs background subtraction on incoming image streams using a selectable algorithm.
  • pix_opencv_bgstats pix_opencv_bgstats performs background and foreground extraction on an incoming image stream, with objects disappearing from the background after a certain period.
  • pix_opencv_bgsubstract pix_opencv_bgsubstract performs simple background subtraction by comparing an image’s color values with a background reference, making it useful for detecting dynamic objects against a static background.
  • pix_opencv_blobtrack pix_opencv_blobtrack implements an all-in-one blob-tracking pipeline for RGBA or grayscale images.
  • pix_opencv_calibration pix_opencv_calibration calibrates a camera from multiple views of a chessboard pattern and then undistorts incoming images.
  • pix_opencv_camshift pix_opencv_camshift uses continuously adaptive mean-shift to track a selected object in a Gem image stream, reporting its center coordinates, width, height, and angle.
  • pix_opencv_clahe pix_opencv_clahe processes incoming GEM pixel data using CLAHE, with controls for the clip limit and tile-grid size.
  • pix_opencv_colorfilt pix_opencv_colorfilt filters video by selecting a color from specified RGB components and applying a tolerance to the color selection.
  • pix_opencv_contours pix_opencv_contours finds contours in an incoming binarized image, passes the GEM list through its first outlet, and outputs contour-related data and summary information from its other outlets.
  • pix_opencv_contours_boundingrect pix_opencv_contours_boundingrect detects multiple contours and calculates an upright bounding rectangle for each detected contour, making it useful for motion tracking when objects are well isolated.
  • pix_opencv_contours_convexhull pix_opencv_contours_convexhull finds the convex hull of the largest detected contour in an image, providing the hull’s vertex count and vertex coordinates.
  • pix_opencv_contours_convexity pix_opencv_contours_convexity finds convexity defects in a detected contour, with each defect defined by a start point, depth point, and end point.
  • pix_opencv_dft pix_opencv_dft calculates the discrete Fourier transform of an image pattern and can be used for pattern matching.
  • pix_opencv_distrans pix_opencv_distrans performs distance processing as a morphology filter that can be used to preprocess images.
  • pix_opencv_edge pix_opencv_edge is an edge-detection filter for image streams in Pd/GEM.
  • pix_opencv_facetracker pix_opencv_facetracker finds and tracks a face in a GEM image stream using the FaceTracker library, passing the gemlist from its inlet to its outlet.
  • pix_opencv_findchessboardcorners pix_opencv_findchessboardcorners searches an image for the inner corners of a chessboard pattern, which is useful for calibrating several cameras together.
  • pix_opencv_floodfill pix_opencv_floodfill marks image components with a fill color and can serve as an object selector in tracking algorithms.
  • pix_opencv_haarcascade pix_opencv_haarcascade detects objects in image frames using a trained cascade classifier, reporting the number of detected objects and, for each detection, its center coordinates and radius.
  • pix_opencv_hist_compare pix_opencv_hist_compare performs image recognition by comparing an input image’s histogram with stored histograms, outputting matching measures and the closest stored histogram as the winner.
  • pix_opencv_hough_circles pix_opencv_hough_circles applies a Hough circle-detection algorithm to image input and reports each detected circle’s X/Y position and radius.
  • pix_opencv_hough_lines pix_opencv_hough_lines applies a Hough line-detection algorithm to an image and reports each detected line as X1, Y1, X2, and Y2 coordinates.
  • pix_opencv_hu_compare pix_opencv_hu_compare compares contours with a reference pattern contour using Hu moments (CvMatchShape) and reports detected contours by position, width, and height.
  • pix_opencv_hu_moments pix_opencv_hu_moments calculates the seven Hu moments (h1–h7) of incoming image frames, allowing moments from images such as simple patterns to be compared.
  • pix_opencv_knear pix_opencv_knear performs OCR-like pattern recognition by comparing an incoming frame with a set of image patterns and outputting the comparison distance.
  • pix_opencv_laplace pix_opencv_laplace applies a Laplace filter and is used as an edge detector.
  • pix_opencv_lk pix_opencv_lk performs Lukas–Kanade corner-point tracking, with corner detection based on the Shi–Tomasi method.
  • pix_opencv_matchshape pix_opencv_matchshape compares a contour against loaded template contours using OpenCV’s cv::matchShapes function to recognize corresponding shapes.
  • pix_opencv_morphology pix_opencv_morphology applies a morphology filter to image data, with open/close and erode/dilate modes, to help focus on bright or dark zones.
  • pix_opencv_motempl pix_opencv_motempl performs OpenCV-based motion detection, reporting each motion component as center X/Y, width, height, and angle; component -1 represents the whole image.
  • pix_opencv_of_bm pix_opencv_of_bm applies a block-matching optical-flow algorithm to an image stream to detect movement, marking the block with the greatest motion using a white arrow.
  • pix_opencv_of_hs pix_opencv_of_hs applies the Horn–Schunck optical-flow algorithm to a video stream to analyze movement.
  • pix_opencv_of_lk pix_opencv_of_lk applies the Lucas–Kanade optical-flow algorithm to calculate movement in an image stream, including the largest movement amplitude, its block angle, and the average block-movement angle.
  • pix_opencv_opticalflow pix_opencv_opticalflow computes optical flow from an RGBA image, producing a gemlist output and an additional info output.
  • pix_opencv_pgh_compare pix_opencv_pgh_compare compares contours from an image or video with a pattern contour and outputs the position and dimensions (X, Y, width, and height) of detected contours.
  • pix_opencv_surf pix_opencv_surf applies SURF (Speeded-Up Robust Features) to image frames for marking and tracking up to 10 points, with optional Delaunay processing.
  • pix_opencv_threshold pix_opencv_threshold performs pixel thresholding and is used as a filter to detect bright or dark pixels.
  • pix_opencv_trackKnn pix_opencv_trackKnn uses the KNN algorithm to keep track of detected features supplied as cvblob lists, and can be used with other tracking techniques.
  • pix_opencv_warpperspective pix_opencv_warpperspective applies a perspective transformation to an image, computing the transformation matrix from source and destination matrices.