|
| 1 | +{ |
| 2 | + "cells": [ |
| 3 | + { |
| 4 | + "cell_type": "markdown", |
| 5 | + "id": "d7f2c5dd", |
| 6 | + "metadata": {}, |
| 7 | + "source": [ |
| 8 | + "# Optical Flow" |
| 9 | + ] |
| 10 | + }, |
| 11 | + { |
| 12 | + "cell_type": "markdown", |
| 13 | + "id": "6e3c585f", |
| 14 | + "metadata": {}, |
| 15 | + "source": [ |
| 16 | + "</br><div align=\"center\"> <b> <font size=\"3\" color='green'>cv2.calcOpticalFlowPyrLK(prevImg, nextImg, prevPts, nextPts, winSize, maxLevel)</font></b> </div>\n", |
| 17 | + "<b>prevImg: </b>first 8-bit input image. </br>\n", |
| 18 | + "<b>nextImg: </b>second input image. </br>\n", |
| 19 | + "<b>prevPts: </b>vector of 2D points for which the flow needs to be found.</br>\n", |
| 20 | + "<b>nextPts: </b>vector of 2D points for which the flow needs to be found.</br>\n", |
| 21 | + "<b>winSize: </b> size of the search window at each pyramid level.</br>\n", |
| 22 | + "<b>maxLevel: </b> 0-based maximal pyramid level number; if set to 0, pyramids are not used (single level), if set to 1, two levels are used, and so on." |
| 23 | + ] |
| 24 | + }, |
| 25 | + { |
| 26 | + "cell_type": "markdown", |
| 27 | + "id": "cf3e22a6", |
| 28 | + "metadata": {}, |
| 29 | + "source": [ |
| 30 | + "</br><div align=\"center\"> <b> <font size=\"3\" color='green'> cv2.calcOpticalFlowFarneback(prev, next, pyr_scale, levels, winsize, iterations, poly_n, poly_sigma)</font></b> </div>\n", |
| 31 | + "\n", |
| 32 | + "<b>prev: </b> First input image in 8-bit single channel format.\n", |
| 33 | + "\n", |
| 34 | + "next : Second input image of same type and same size as prev.\n", |
| 35 | + "\n", |
| 36 | + "pyr_scale : parameter specifying the image scale to build pyramids for each image (scale < 1). A classic pyramid is of \n", |
| 37 | + "generally 0.5 scale, every new layer added, it is halved to the previous one.\n", |
| 38 | + "\n", |
| 39 | + "levels : levels=1 says, there are no extra layers (only the initial image) . It is the number of pyramid layers including the first image.\n", |
| 40 | + "\n", |
| 41 | + "winsize : It is the average window size, larger the size, the more robust the algorithm is to noise, and provide fast motion detection, though gives blurred motion fields.\n", |
| 42 | + "\n", |
| 43 | + "iterations : Number of iterations to be performed at each pyramid level.\n", |
| 44 | + "\n", |
| 45 | + "poly_n : It is typically 5 or 7, it is the size of the pixel neighbourhood which is used to find polynomial expansion between the pixels.\n", |
| 46 | + "\n", |
| 47 | + "poly_sigma : standard deviation of the gaussian that is for derivatives to be smooth as the basis of the polynomial expansion. It can be 1.1 for poly= 5 and 1.5 for poly= 7." |
| 48 | + ] |
| 49 | + } |
| 50 | + ], |
| 51 | + "metadata": { |
| 52 | + "kernelspec": { |
| 53 | + "display_name": "Python 3 (ipykernel)", |
| 54 | + "language": "python", |
| 55 | + "name": "python3" |
| 56 | + }, |
| 57 | + "language_info": { |
| 58 | + "codemirror_mode": { |
| 59 | + "name": "ipython", |
| 60 | + "version": 3 |
| 61 | + }, |
| 62 | + "file_extension": ".py", |
| 63 | + "mimetype": "text/x-python", |
| 64 | + "name": "python", |
| 65 | + "nbconvert_exporter": "python", |
| 66 | + "pygments_lexer": "ipython3", |
| 67 | + "version": "3.7.11" |
| 68 | + } |
| 69 | + }, |
| 70 | + "nbformat": 4, |
| 71 | + "nbformat_minor": 5 |
| 72 | +} |
0 commit comments