# Regular Meeting (2020.2.17) ## Completed * Ubderstanding what *Hough Transform* is ## Doing now * How Hough-Transform worked in 2D-Tracker * Testing GTY transceiver(Some parameter I don't know how to setting) ## The Hough Transform **Normal usage of Hough Transform** ![hough-result](https://i.imgur.com/HYWt6I6.png) **Used in Tracker on Belle-II** ![b2dtrc](https://i.imgur.com/cwiSHiM.png) ### Space #### 1. x-y Space $f(x,y)$ => $y = ax + b$ $a$: slope $b$: intercept if we fixed $a = 0.5, b= 4.5$ chart of $y = 0.5x + 4.5$ ![xy-space](https://i.imgur.com/jWqH7Pt.png) #### 2. a-b Space $g(a,b)$ => $b = -ax + y$ if we fixed $x = 0.5, y = 4.5$ => $b = -0.5a + 4.5$ chart of $b = -0.5a + 4.5$ ![ab-space](https://i.imgur.com/JqrzkCW.png) (slope = $-a/b$ = tan($\theta$)) #### 3. Represent a-b Space with r-$\theta$ Space h(r,$\theta$) => r = xcos($\theta$) + ysin($\theta$) ![r-th](https://i.imgur.com/uCTAxu3.png) if we mapping a linear eq.(a-b space) to r-$\theta$ space ![th-xt](https://i.imgur.com/XVO8edR.png) ### 4. Accumulator with r-$\theta$ Space ![acc-1](https://i.imgur.com/4nz9QbX.png) ![rotate](https://docs.opencv.org/3.4.9/houghlinesdemo.gif) #### folw of Hough Algorithm r-$\theta$ Space 1. Filtering input data or image(not found in paper) 2. Calculating (r,$\theta$) for each point which stayed after step 1 3. Choosing (r,$\theta$) with threshold 4. Rebuilding line with (r,$\theta$) ###### tags: `Regular Meeting` `DeWei`