*VERSION 3.25 OF TOOLBOX*

diff --git a/doc/channels/Contents.html b/doc/channels/Contents.html
index f3e327885ac48e82f1dbb209df2a0500aacc005b..84a0c2b8f2b0d0b063e27b60b481d6845ae8d5c3 100644 (file)
--- a/doc/channels/Contents.html
+++ b/doc/channels/Contents.html
@@ -33,7 +33,10 @@
    "The Fastest Pedestrian Detector in the West," BMVC 2010.\r
   [3] P. Dollár, R. Appel and W. Kienzle\r
    "Crosstalk Cascades for Frame-Rate Pedestrian Detection," ECCV 2012.\r
+  [4] P. Dollár, R. Appel, S. Belongie and P. Perona\r
+   "Fast Feature Pyramids for Object Detection", PAMI 2014.\r
  Please cite a subset of the above papers if you end up using the code.\r
+ The PAMI 2014 paper has the most thorough and up to date descriptions.\r
  Code written and maintained by Piotr Dollar and Ron Appel.\r
 \r
  Channels:\r

diff --git a/doc/channels/chnsPyramid.html b/doc/channels/chnsPyramid.html
index 063ddc85c164baeb8d578a19016a00751ecf7f12..f28fcdbf7d27d30620d58ae16a69c3c07cca25b8 100644 (file)
--- a/doc/channels/chnsPyramid.html
+++ b/doc/channels/chnsPyramid.html
@@ -46,8 +46,8 @@
  can be used to approximate feature responses at nearby scales. The\r
  approximation is accurate at least within an entire scale octave. For\r
  details and to understand why this unexpected result holds, please see:\r
-   P. Dollár, S. Belongie and P. Perona\r
-   "The Fastest Pedestrian Detector in the West," BMVC 2010.\r
+   P. Dollár, R. Appel, S. Belongie and P. Perona\r
+   "Fast Feature Pyramids for Object Detection", PAMI 2014.\r
 \r
  The parameter "nApprox" determines how many intermediate scales are\r
  approximated using the techniques described in the above paper. Roughly\r
@@ -131,8 +131,8 @@
 \r
  See also <a href="chnsCompute.html" class="code" title="function chns = chnsCompute( I, varargin )">chnsCompute</a>, <a href="chnsScaling.html" class="code" title="function [lambdas,as,scales,fs] = chnsScaling( pChns, Is, show )">chnsScaling</a>, <a href="convTri.html" class="code" title="function J = convTri( I, r, s, nomex )">convTri</a>, <a href="imPad.html" class="code" title="function J = imPad( I, pad, type )">imPad</a>\r
 \r
- Piotr's Image&amp;Video Toolbox      Version 3.02\r
- Copyright 2012 Piotr Dollar &amp; Ron Appel.  [pdollar-at-caltech.edu]\r
+ Piotr's Image&amp;Video Toolbox      Version 3.25\r
+ Copyright 2013 Piotr Dollar &amp; Ron Appel.  [pdollar-at-caltech.edu]\r
  Please email me if you find bugs, or have suggestions or questions!\r
  Licensed under the Simplified BSD License [see external/bsd.txt]</pre></div>\r
 \r

diff --git a/doc/channels/chnsScaling.html b/doc/channels/chnsScaling.html
index f6e03338d16197b244d0da84cab202d7efaa52ab..889b93bd7616abc8f4bb5e1bedd88213320b3987 100644 (file)
--- a/doc/channels/chnsScaling.html
+++ b/doc/channels/chnsScaling.html
@@ -30,8 +30,8 @@
  can be used to approximate feature responses at nearby scales. The\r
  approximation is accurate at least within an entire scale octave. For\r
  details and to understand why this unexpected result holds, please see:\r
-   P. Dollár, S. Belongie and P. Perona\r
-   "The Fastest Pedestrian Detector in the West," BMVC 2010.\r
+   P. Dollár, R. Appel, S. Belongie and P. Perona\r
+   "Fast Feature Pyramids for Object Detection", PAMI 2014.\r
 \r
  This function computes channels at multiple image scales and plots the\r
  resulting power law scaling. The purpose of this function is two-fold:\r
@@ -62,14 +62,14 @@
   fs             - [nImages x nScales x nTypes] array of feature means\r
 \r
  EXAMPLE\r
-  sDir='E:/code/detector/pedsData/train/negBig';\r
+  sDir = 'data/Inria/train/neg/';\r
   Is = fevalImages( @(x) {x}, {}, sDir, 'I', 'png', 0, 200 );\r
   p = chnsCompute(); lambdas = chnsScaling( p, Is, 1 );\r
 \r
  See also <a href="chnsCompute.html" class="code" title="function chns = chnsCompute( I, varargin )">chnsCompute</a>, <a href="chnsPyramid.html" class="code" title="function pyramid = chnsPyramid( I, varargin )">chnsPyramid</a>, fevalImages\r
 \r
- Piotr's Image&amp;Video Toolbox      Version 3.02\r
- Copyright 2012 Piotr Dollar &amp; Ron Appel.  [pdollar-at-caltech.edu]\r
+ Piotr's Image&amp;Video Toolbox      Version 3.25\r
+ Copyright 2013 Piotr Dollar &amp; Ron Appel.  [pdollar-at-caltech.edu]\r
  Please email me if you find bugs, or have suggestions or questions!\r
  Licensed under the Simplified BSD License [see external/bsd.txt]</pre></div>\r
 \r

diff --git a/doc/detector/Contents.html b/doc/detector/Contents.html
index 0f530c8159bbe20582f2123b5e66b782481c9d0b..1d58757f462e2cdefef06397f41d05e4789dc7d6 100644 (file)
--- a/doc/detector/Contents.html
+++ b/doc/detector/Contents.html
@@ -33,7 +33,10 @@
    "The Fastest Pedestrian Detector in the West," BMVC 2010.\r
   [3] P. Dollár, R. Appel and W. Kienzle\r
    "Crosstalk Cascades for Frame-Rate Pedestrian Detection," ECCV 2012.\r
+  [4] P. Dollár, R. Appel, S. Belongie and P. Perona\r
+   "Fast Feature Pyramids for Object Detection", PAMI 2014.\r
  Please cite a subset of the above papers if you end up using the code.\r
+ The PAMI 2014 paper has the most thorough and up to date descriptions.\r
  Code written and maintained by Piotr Dollar and Ron Appel.\r
 \r
  Aggregate channel features object detector:\r

diff --git a/doc/detector/acfTrain.html b/doc/detector/acfTrain.html
index c8fd45ff96ad1fb359d69528b029fafa859f5243..a44fc564e1bec3a5004e8766a64c11e5201c1394 100644 (file)
--- a/doc/detector/acfTrain.html
+++ b/doc/detector/acfTrain.html
@@ -25,11 +25,11 @@
 <h2><a name="_description"></a>DESCRIPTION <a href="#_top"><img alt="^" border="0" src="../up.png"></a></h2>\r
 <div class="fragment"><pre class="comment"> Train aggregate channel features object detector.\r
 \r
- Train aggregate channel features (ACF) object detector:\r
-  P. Dollár, Z. Tu, P. Perona and S. Belongie\r
-  &quot;Integral Channel Features&quot;, BMVC 2009.\r
- The exact details of the algorithm below differ substantially from the\r
- BMVC09 paper, a more up-to-date method writeup is not yet available.\r
+ Train aggregate channel features (ACF) object detector as described in:\r
+  P. Dollár, R. Appel, S. Belongie and P. Perona\r
+   &quot;Fast Feature Pyramids for Object Detection&quot;, PAMI 2014.\r
+ The ACF detector is fast (30 fps on a single core) and achieves top\r
+ accuracy on rigid object detection.\r
 \r
  Takes a set of parameters opts (described in detail below) and trains a\r
  detector from start to finish including performing multiple rounds of\r
@@ -129,7 +129,7 @@
  See also <a href="acfDetect.html" class="code" title="function bbs = acfDetect( I, detector, fileName )">acfDetect</a>, <a href="acfDemoInria.html" class="code" title="">acfDemoInria</a>, <a href="acfModify.html" class="code" title="function detector = acfModify( detector, varargin )">acfModify</a>, <a href="acfTest.html" class="code" title="function [miss,roc,gt,dt] = acfTest( varargin )">acfTest</a>, chnsCompute,\r
  chnsPyramid, adaBoostTrain, <a href="bbGt.html" class="code" title="function varargout = bbGt( action, varargin )">bbGt</a>, <a href="bbNms.html" class="code" title="function bbs = bbNms( bbs, varargin )">bbNms</a>, jitterImage\r
 \r
- Piotr's Image&amp;Video Toolbox      Version 3.22\r
+ Piotr's Image&amp;Video Toolbox      Version 3.25\r
  Copyright 2013 Piotr Dollar &amp; Ron Appel.  [pdollar-at-caltech.edu]\r
  Please email me if you find bugs, or have suggestions or questions!\r
  Licensed under the Simplified BSD License [see external/bsd.txt]</pre></div>\r

diff --git a/doc/history.txt b/doc/history.txt
index 1b8f288f1791d5a6860e7ad635ae6a0fbcd002e1..b83b2509288d71861e2c177b1eb1617d1c7d29a3 100644 (file)
--- a/doc/history.txt
+++ b/doc/history.txt
@@ -1,3 +1,7 @@
+Version 3.25 (15-Dec-2013)\r
+ -added pointer to PAMI14 work: chnsScaling.m, acfTrain.m, chnsPyramid.m\r
+ -minor: toolboxCompile.m\r
+\r
 Version 3.24 (10-Oct-2013)\r
  -classify/private/*.cpp: minor fixes for very large datasets\r
  -classify/forest*.m: added new options for splitting/applying \r

diff --git a/doc/overview.html b/doc/overview.html
index c21d37664bbccdb4a9b821869ea529e9c42333f0..fe2bbccbec6cb8b2f55e0af4662ac5528cabb107 100644 (file)
--- a/doc/overview.html
+++ b/doc/overview.html
@@ -40,12 +40,11 @@
  <p><strong>For version history click <a href="history.txt">here.</a>\r
  This code is licensed under the <a href="http://en.wikipedia.org/wiki/BSD_licenses" target="blank">Simplified BSD License.</a></strong></p>\r
  <ul>\r
-  <li><a href="../piotr_toolbox.zip">Version 3.24</a> &nbsp; Oct. 10, 2013 &nbsp; [current stable version]\r
+  <li><a href="../piotr_toolbox.zip">Version 3.25</a> &nbsp; Dec. 15, 2013 &nbsp; [current stable version]\r
   <li><a href="../piotr_toolbox_V1.03.zip">Version 1.03</a> &nbsp; May. 03, 2006 &nbsp; [compatible with cuboids code]\r
   <li><a href="../">All Versions</a>\r
  </ul>\r
- </div>\r
-\r
+  <p>Requires Matlab 2011b or later and Matlab's Image Processing Toolbox.</p>\r
 </div>\r
 \r
 <h2>INSTALL<a href="#_top"><img alt=^ src="up.png" border=0 /></a></h2>\r
@@ -54,8 +53,8 @@
  <br/>&nbsp; &gt;&gt; addpath(genpath('c:\toolbox')); savepath;</p>\r
  <p>If needed, run the compile script for the mex files:\r
    <br/>&nbsp; &gt;&gt; toolboxCompile;\r
-   <br/>Note: 64 bit Windows/Linux binaries are already included.\r
- </p> \r
+  <br/>Note: 64 bit Windows/Linux binaries are already included.\r
+ </p>\r
 </div>\r
 \r
 <h2>CITE<a href="#_top"><img alt=^ src="up.png" border=0 /></a></h2>\r
@@ -73,7 +72,7 @@
 <div class=box>\r
  If you have a question or a suggestion, or if you find a bug,\r
  please email me at<font style="BACKGROUND-COLOR: #f5f5f5" color=#0000ff>\r
- pdollar-at-caltech.edu</font></div>\r
+ pdollar-at-caltech.edu</font>\r
 </div>\r
 \r
 <!-- Start of Google Analytics Code -->\r

diff --git a/external/history.txt b/external/history.txt
index 09681814c8ebfe9787e2de53bb9ad9fb2ab41b9a..b83b2509288d71861e2c177b1eb1617d1c7d29a3 100644 (file)
--- a/external/history.txt
+++ b/external/history.txt
@@ -1,4 +1,4 @@
-Version NEW\r
+Version 3.25 (15-Dec-2013)\r
  -added pointer to PAMI14 work: chnsScaling.m, acfTrain.m, chnsPyramid.m\r
  -minor: toolboxCompile.m\r
 \r

diff --git a/external/m2html/templates/frame-piotr/overview.html b/external/m2html/templates/frame-piotr/overview.html
index fb267ad1f2bb63c7ce4353c01a484eb792fd85dd..fe2bbccbec6cb8b2f55e0af4662ac5528cabb107 100644 (file)
--- a/external/m2html/templates/frame-piotr/overview.html
+++ b/external/m2html/templates/frame-piotr/overview.html
@@ -40,7 +40,7 @@
  <p><strong>For version history click <a href="history.txt">here.</a>\r
  This code is licensed under the <a href="http://en.wikipedia.org/wiki/BSD_licenses" target="blank">Simplified BSD License.</a></strong></p>\r
  <ul>\r
-  <li><a href="../piotr_toolbox.zip">Version 3.24</a> &nbsp; Oct. 10, 2013 &nbsp; [current stable version]\r
+  <li><a href="../piotr_toolbox.zip">Version 3.25</a> &nbsp; Dec. 15, 2013 &nbsp; [current stable version]\r
   <li><a href="../piotr_toolbox_V1.03.zip">Version 1.03</a> &nbsp; May. 03, 2006 &nbsp; [compatible with cuboids code]\r
   <li><a href="../">All Versions</a>\r
  </ul>\r