Databases
StackOverflow2013
Postsdbo
POFast Gaussian Blur image filter with ARM NEON
 

Note that there are some explanatory texts on larger screens.

plurals
  1. POFast Gaussian Blur image filter with ARM NEON
    primarykey
    data
    text
    <p>I'm trying to make a mobile fast version of Gaussian Blur image filter.</p> <p>I've read other questions, like: <a href="https://stackoverflow.com/questions/9158818/fast-gaussian-blur-on-unsigned-char-image-arm-neon-intrinsics-ios-dev?answertab=votes#tab-top">Fast Gaussian blur on unsigned char image- ARM Neon Intrinsics- iOS Dev</a></p> <p>For my purpose i need only a fixed size (7x7) fixed sigma (2) Gaussian filter.</p> <p>So, before optimizing for ARM NEON, I'm implementing 1D Gaussian Kernel in C++, and comparing performance with OpenCV GaussianBlur() method directly in mobile environment (Android with NDK). This way it will result in a much simpler code to optimize.</p> <p>However the result is that my implementation is 10 times slower then OpenCV4Android version. I've read that OpenCV4 Tegra have optimized GaussianBlur implementation, but I don't think that standard OpenCV4Android have those kind of optimizations, so why is my code so slow?</p> <p>Here is my implementation (note: reflect101 is used for pixel reflection when applying filter near borders):</p> <pre><code>Mat myGaussianBlur(Mat src){ Mat dst(src.rows, src.cols, CV_8UC1); Mat temp(src.rows, src.cols, CV_8UC1); float sum, x1, y1; // coefficients of 1D gaussian kernel with sigma = 2 double coeffs[] = {0.06475879783, 0.1209853623, 0.1760326634, 0.1994711402, 0.1760326634, 0.1209853623, 0.06475879783}; //Normalize coeffs float coeffs_sum = 0.9230247873f; for (int i = 0; i &lt; 7; i++){ coeffs[i] /= coeffs_sum; } // filter vertically for(int y = 0; y &lt; src.rows; y++){ for(int x = 0; x &lt; src.cols; x++){ sum = 0.0; for(int i = -3; i &lt;= 3; i++){ y1 = reflect101(src.rows, y - i); sum += coeffs[i + 3]*src.at&lt;uchar&gt;(y1, x); } temp.at&lt;uchar&gt;(y,x) = sum; } } // filter horizontally for(int y = 0; y &lt; src.rows; y++){ for(int x = 0; x &lt; src.cols; x++){ sum = 0.0; for(int i = -3; i &lt;= 3; i++){ x1 = reflect101(src.rows, x - i); sum += coeffs[i + 3]*temp.at&lt;uchar&gt;(y, x1); } dst.at&lt;uchar&gt;(y,x) = sum; } } return dst; } </code></pre>
    singulars
    1. PO
      singulars
      1. PTAnswer
    1. This table or related slice is empty.
    1. PTQuestion
    1. USCommunity
    1. USAlessandro Gaietta
    plurals
    1. PL
      singulars
      1. LTLinked
    1. This table or related slice is empty.
    1. This table or related slice is empty.
    1. PO
      singulars
      1. PTAnswer
    2. PO
      singulars
      1. PTAnswer
    3. PO
      singulars
      1. PTAnswer
    1. VO
      singulars
      1. POFast Gaussian Blur image filter with ARM NEON
      1. This table or related slice is empty.
      1. VTDownMod
    2. VO
      singulars
      1. POFast Gaussian Blur image filter with ARM NEON
      1. This table or related slice is empty.
      1. VTUpMod
    3. VO
      singulars
      1. POFast Gaussian Blur image filter with ARM NEON
      1. This table or related slice is empty.
      1. VTUpMod
    1. COEDIT: there is probably a little error in the reflect101, their argument should be (src.cols, y+i) and (src.rows, x+i).
      singulars
      1. POFast Gaussian Blur image filter with ARM NEON
      1. USAlessandro Gaietta
 

Querying!

 
Guidance
A row detail

Detail views are divided into sections. All the information in the data section comes from columns in the selected row. The other sections display data from other, related rows.

Related data can be related in a to-one or a to-many fashion. Captions of data related in a to-many fashion link to a list view showing a filtered view of the table.

Try moving around until you find a non-empty to-many entry and click on the label to get to one. You can move back to the root by clicking on the database name in the header.

SQuiL has stopped working due to an internal error.

If you are curious you may find further information in the browser console, which is accessible through the devtools (F12).

Reload