📄 makeltusegmentnetwork.html
字号:
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN" "http://www.w3.org/TR/REC-html40/loose.dtd"><html><head> <title>Description of makeLTUsegmentNetwork</title> <meta name="keywords" content="makeLTUsegmentNetwork"> <meta name="description" content="makeLTUsegmentNetwork - creates an LTU network for map segmentation."> <meta http-equiv="Content-Type" content="text/html; charset=iso-8859-1"> <meta name="generator" content="m2html © 2003 Guillaume Flandin"> <meta name="robots" content="index, follow"> <link type="text/css" rel="stylesheet" href="../m2html.css"></head><body><a name="_top"></a><div><a href="../index.html">Home</a> > <a href="#">mfiles</a> > makeLTUsegmentNetwork.m</div><!--<table width="100%"><tr><td align="left"><a href="../index.html"><img alt="<" border="0" src="../left.png"> Master index</a></td><td align="right"><a href="index.html">Index for .\mfiles <img alt=">" border="0" src="../right.png"></a></td></tr></table>--><h1>makeLTUsegmentNetwork</h1><h2><a name="_name"></a>PURPOSE <a href="#_top"><img alt="^" border="0" src="../up.png"></a></h2><div class="box"><strong>makeLTUsegmentNetwork - creates an LTU network for map segmentation.</strong></div><h2><a name="_synopsis"></a>SYNOPSIS <a href="#_top"><img alt="^" border="0" src="../up.png"></a></h2><div class="box"><strong>function LTUnetwork = makeLTUsegmentNetwork(mapSize,thresh) </strong></div><h2><a name="_description"></a>DESCRIPTION <a href="#_top"><img alt="^" border="0" src="../up.png"></a></h2><div class="fragment"><pre class="comment"> makeLTUsegmentNetwork - creates an LTU network for map segmentation. LTUnetwork = makeLTUSsegmentNetwork(mapSize,thresh) Creates a network of linear threshold units for segmenting a map of size mapSize with threshold thresh. See section 3 of this paper for details: Walther, D., and Koch, C. (2006). Modeling attention to salient proto-objects. Neural Networks 19, pp. 1395-1407. See also <a href="LTUsegmentMap.html" class="code" title="function [resultMap,segMaps] = LTUsegmentMap(map,seedPoint,varargin)">LTUsegmentMap</a>, <a href="LTUsimulate.html" class="code" title="function [output,newStates] = LTUsimulate(LTUnetwork,states,inputs,numIter)">LTUsimulate</a>, <a href="dataStructures.html" class="code" title="">dataStructures</a>.</pre></div><!-- crossreference --><h2><a name="_cross"></a>CROSS-REFERENCE INFORMATION <a href="#_top"><img alt="^" border="0" src="../up.png"></a></h2>This function calls:<ul style="list-style-image:url(../matlabicon.gif)"></ul>This function is called by:<ul style="list-style-image:url(../matlabicon.gif)"><li><a href="LTUsegmentMap.html" class="code" title="function [resultMap,segMaps] = LTUsegmentMap(map,seedPoint,varargin)">LTUsegmentMap</a> LTUsegmentMap - segment map using a network of linear threshold units.</li></ul><!-- crossreference --><h2><a name="_source"></a>SOURCE CODE <a href="#_top"><img alt="^" border="0" src="../up.png"></a></h2><div class="fragment"><pre>0001 <span class="comment">% makeLTUsegmentNetwork - creates an LTU network for map segmentation.</span>0002 <span class="comment">%</span>0003 <span class="comment">% LTUnetwork = makeLTUSsegmentNetwork(mapSize,thresh)</span>0004 <span class="comment">% Creates a network of linear threshold units for segmenting</span>0005 <span class="comment">% a map of size mapSize with threshold thresh.</span>0006 <span class="comment">% See section 3 of this paper for details:</span>0007 <span class="comment">% Walther, D., and Koch, C. (2006). Modeling attention to salient</span>0008 <span class="comment">% proto-objects. Neural Networks 19, pp. 1395-1407.</span>0009 <span class="comment">%</span>0010 <span class="comment">% See also LTUsegmentMap, LTUsimulate, dataStructures.</span>0011 0012 <span class="comment">% This file is part of the SaliencyToolbox - Copyright (C) 2006-2007</span>0013 <span class="comment">% by Dirk B. Walther and the California Institute of Technology.</span>0014 <span class="comment">% See the enclosed LICENSE.TXT document for the license agreement.</span>0015 <span class="comment">% More information about this project is available at:</span>0016 <span class="comment">% http://www.saliencytoolbox.net</span>0017 0018 <a name="_sub0" href="#_subfunctions" class="code">function LTUnetwork = makeLTUsegmentNetwork(mapSize,thresh)</a>0019 0020 numPix = prod(mapSize);0021 h = mapSize(1);0022 w = mapSize(2);0023 0024 units = 5;0025 numCells = numPix * units;0026 0027 <span class="comment">% set up the connection matrix as a sparse matrix</span>0028 con = sparse(numCells,numCells);0029 0030 <span class="comment">% now wire up all the connections</span>0031 <span class="comment">% cell 1 is the input from the select signal</span>0032 <span class="comment">% cell 2 is the input from the image</span>0033 <span class="comment">% cell 3 is an inhibitory interneuron fed from cell 2</span>0034 <span class="comment">% cell 4 pools the lateral input from the neighbors (P cell)</span>0035 <span class="comment">% cell 5 computes the output from all this (S cell)</span>0036 0037 <span class="comment">% set up the network connections</span>0038 hunits = h * units;0039 <span class="keyword">for</span> x = 1:w0040 <span class="keyword">for</span> y = 1:h0041 base = (x-1)*hunits + (y-1)*units + 1;0042 0043 <span class="comment">% cell 1 to cell 5</span>0044 con(base,base+4) = 1;0045 0046 <span class="comment">% cell 2 to cell 3 to cell 5</span>0047 con(base+1,base+2) = -1;0048 con(base+2,base+4) = -2;0049 0050 <span class="comment">% inputs from neighboring pixels to cell 4</span>0051 <span class="keyword">if</span> (x > 1) con(base-hunits+4,base+3) = 1; <span class="keyword">end</span>0052 <span class="keyword">if</span> (x < w) con(base+hunits+4,base+3) = 1; <span class="keyword">end</span>0053 <span class="keyword">if</span> (y > 1) con(base- units+4,base+3) = 1; <span class="keyword">end</span>0054 <span class="keyword">if</span> (y < h) con(base+ units+4,base+3) = 1; <span class="keyword">end</span>0055 0056 <span class="comment">% finally, connect cell 4 to cell 5</span>0057 con(base+3,base+4) = 1;0058 <span class="keyword">end</span>0059 <span class="keyword">end</span>0060 0061 LTUnetwork.connections = con;0062 LTUnetwork.thresholds = repmat([0 0 -thresh 1 1],1,numPix);0063 idx = ([1:numPix] - 1) * units + 1;0064 LTUnetwork.input_idx = [idx+1,idx];0065 LTUnetwork.output_idx = idx+4;0066 LTUnetwork.numCells = numCells;0067 LTUnetwork.label = sprintf(<span class="string">'segmentation network for %d x %d maps'</span>,w,h);</pre></div><hr><address>Generated on Fri 07-Sep-2007 14:42:18 by <strong><a href="http://www.artefact.tk/software/matlab/m2html/">m2html</a></strong> © 2003</address></body></html>⌨️ 快捷键说明
复制代码
Ctrl + C
搜索代码
Ctrl + F
全屏模式
F11
切换主题
Ctrl + Shift + D
显示快捷键
?
增大字号
Ctrl + =
减小字号
Ctrl + -