Added two filtering options to pLoad to set the "ignore" flag when us…

detector/bbGt.m

@@ -198,7 +198,20 @@
 %   .oRng     - [] range of acceptable obj orientations (angles)
 %   .xRng     - [] range of x coordinates of bb extent
 %   .yRng     - [] range of y coordinates of bb extent
+%   .zRng     - [] range of acceptable z point coordinates
 %   .vRng     - [] range of acceptable obj occlusion levels
+%   .name     - [] regexp on image source name to ignore
+%   .invName  - [0] invert behavior of name, setting non-matches ignore
+%   .database - [] regexp on database name to ignore
+%   .invData  - [0] invert behavior of database, setting non-matches to
+%               ignore
+%   .ignDiff  - [1] ignore labels marked as "difficult" in Pascal VOC
+%               format (1). Has no effect in other formats. Valid values
+%               and effects on use of difficult lables are
+%               0  - labels are used as normal
+%               1  - labels are set to ignore
+%               -1 - difficult labels are used, and all labels not set as 
+%                    difficult are set to ignore
 %
 % OUTPUTS
 %  objs     - loaded objects
@@ -210,11 +223,16 @@
 
 % get parameters
 df={'format',0,'ellipse',1,'squarify',[],'lbls',[],'ilbls',[],'hRng',[],...
-  'wRng',[],'aRng',[],'arRng',[],'oRng',[],'xRng',[],'yRng',[],'vRng',[]};
-[format,ellipse,sqr,lbls,ilbls,hRng,wRng,aRng,arRng,oRng,xRng,yRng,vRng]...
+  'wRng',[],'aRng',[],'arRng',[],'oRng',[],'xRng',[],'yRng',[],...
+  'zRng',[],'vRng',[],...
+  'name',[],'invName',0,'database',[],'invData',0,'ignDiff',1};
+[format,ellipse,sqr,lbls,ilbls,hRng,wRng,aRng,arRng,oRng,xRng,yRng,zRng,vRng,...
+  name,invName,database,invData,ignDiff]...
   = getPrmDflt(varargin,df,1);
 
 % load objs
+nameVal = [];
+dbVal = [];
 if( format==0 )
   % load objs stored in default format
   fId=fopen(fName);
@@ -237,19 +255,41 @@
   % load objs stored in PASCAL VOC format
   if(exist('PASreadrecord.m','file')~=2)
     error('bbLoad() requires the PASCAL VOC code.'); end
-  os=PASreadrecord(fName); os=os.objects;
+  parsed=PASreadrecord(fName);
+  nameVal = parsed.source.image;
+  dbVal = parsed.database;
+  os=parsed.objects;
   n=length(os); objs=create(n);
   if(~isfield(os,'occluded')), for i=1:n, os(i).occluded=0; end; end
+  for i=1:n
+    if(isfield(os(i),'point')) && isfield(os(i).point, 'z')
+      objs(i).z=os(i).point.z;
+    else
+      objs(i).z=nan;
+    end; 
+  end
   for i=1:n
     bb=os(i).bbox; bb(3)=bb(3)-bb(1); bb(4)=bb(4)-bb(2); objs(i).bb=bb;
-    objs(i).lbl=os(i).class; objs(i).ign=os(i).difficult;
+    objs(i).lbl=os(i).class;
+    switch ignDiff
+      case 1
+        objs(i).ign=os(i).difficult;
+      case -1
+        objs(i).ign=not(os(i).difficult);
+      case 0
+      otherwise
+        error('Invalid value for ignDiff')
+    end
     objs(i).occ=os(i).occluded || os(i).truncated;
     if(objs(i).occ), objs(i).bbv=bb; end
   end
 elseif( format==2 )
   if(exist('VOCreadxml.m','file')~=2)
     error('bbLoad() requires the ImageNet dev code.'); end
-  os=VOCreadxml(fName); os=os.annotation;
+  parsed=VOCreadxml(fName);
+  nameVal = parsed.annotation.source.image;
+  dbVal = parsed.annotation.source.database;
+  os=parsed.annotation;
   if(isfield(os,'object')), os=os.object; else os=[]; end
   n=length(os); objs=create(n);
   for i=1:n
@@ -260,6 +300,20 @@
 else error('bbLoad() unknown format: %i',format);
 end
 
+% Filter on image source and database name
+filteredAll = false;
+if ~isempty(nameVal) && ~isempty(name)
+  match = regexp(nameVal, name, 'once');
+  filteredAll = filteredAll | xor(numel(match), invName);
+end
+if ~isempty(dbVal) && ~isempty(database)
+  match = regexp(dbVal, database, 'once');
+  filteredAll = filteredAll | xor(numel(match), invData);
+end
+if filteredAll
+  for i=1:n, objs(i).ign = 1; end
+end
+
 % only keep objects whose lbl is in lbls or ilbls
 if(~isempty(lbls) || ~isempty(ilbls)), K=true(n,1);
   for i=1:n, K(i)=any(strcmp(objs(i).lbl,[lbls ilbls])); end
@@ -293,6 +347,8 @@
       v=(bbv(3)*bbv(4))/(bb(3)*bb(4)); end
     objs(i).ign = objs(i).ign || v<vRng(1) || v>vRng(2); end
 end
+if(~isempty(zRng)),  for i=1:n, v=objs(i).z; % Handle NaN entries
+    objs(i).ign = objs(i).ign || ~(v>zRng(1) && v<zRng(2)); end; end
 
 % finally get extent of each bounding box (not trivial if ang~=0)
 if(nargout<=1), return; end; if(n==0), bbs=zeros(0,5); return; end

external/VOCdevkit/VOCcode/PASemptyobject.m

@@ -0,0 +1,11 @@
+function object=PASemptyobject
+  object.label='';
+  object.orglabel='';
+  object.bbox=[];
+  object.polygon=[];
+  object.mask='';
+  object.class='';
+  object.view='';
+  object.truncated=false;
+  object.difficult=false;
+return

external/VOCdevkit/VOCcode/PASemptyrecord.m

@@ -0,0 +1,6 @@
+function record=PASemptyrecord
+  record.imgname='';
+  record.imgsize=[];
+  record.database='';
+  record.objects=PASemptyobject;
+return

external/VOCdevkit/VOCcode/PASerrmsg.m

@@ -0,0 +1,7 @@
+function PASerrmsg(PASerr,SYSerr)
+  fprintf('Pascal Error Message: %s\n',PASerr);
+  fprintf('System Error Message: %s\n',SYSerr);
+  k=input('Enter K for keyboard, any other key to continue or ^C to quit ...','s');
+  if (~isempty(k)), if (lower(k)=='k'), keyboard; end; end;
+  fprintf('\n');
+return

external/VOCdevkit/VOCcode/PASreadrecord.m

@@ -0,0 +1,11 @@
+function rec = PASreadrecord(path)
+
+if length(path)<4
+    error('unable to determine format: %s',path);
+end
+
+if strcmp(path(end-3:end),'.txt')
+    rec=PASreadrectxt(path);
+else
+    rec=VOCreadrecxml(path);
+end

external/VOCdevkit/VOCcode/PASreadrectxt.m

@@ -0,0 +1,99 @@
+function record=PASreadrectxt(filename)
+  [fd,syserrmsg]=fopen(filename,'rt');
+  if (fd==-1),
+    PASmsg=sprintf('Could not open %s for reading',filename);
+    PASerrmsg(PASmsg,syserrmsg); 
+  end;
+
+  matchstrs=initstrings;
+  record=PASemptyrecord;
+  notEOF=1;
+  while (notEOF),
+    line=fgetl(fd);
+    notEOF=ischar(line);
+    if (notEOF),
+      matchnum=match(line,matchstrs);
+      switch matchnum,
+    case 1, [imgname]=strread(line,matchstrs(matchnum).str);
+	        record.imgname=char(imgname);
+	case 2, [x,y,c]=strread(line,matchstrs(matchnum).str);
+	        record.imgsize=[x y c];
+	case 3, [database]=strread(line,matchstrs(matchnum).str);
+	        record.database=char(database);
+	case 4, [obj,lbl,xmin,ymin,xmax,ymax]=strread(line,matchstrs(matchnum).str);
+	        record.objects(obj).label=char(lbl);
+		record.objects(obj).bbox=[min(xmin,xmax),min(ymin,ymax),max(xmin,xmax),max(ymin,ymax)];
+	case 5, tmp=findstr(line,' : ');
+	        [obj,lbl]=strread(line(1:tmp),matchstrs(matchnum).str);
+	        record.objects(obj).label=char(lbl);
+    		record.objects(obj).polygon=sscanf(line(tmp+3:end),'(%d, %d) ')';
+	case 6, [obj,lbl,mask]=strread(line,matchstrs(matchnum).str);
+	        record.objects(obj).label=char(lbl);
+    		record.objects(obj).mask=char(mask);
+	case 7, [obj,lbl,orglbl]=strread(line,matchstrs(matchnum).str);
+            lbl=char(lbl);
+	        record.objects(obj).label=lbl;
+    		record.objects(obj).orglabel=char(orglbl);
+            if strcmp(lbl(max(end-8,1):end),'Difficult')
+                record.objects(obj).difficult=true;
+                lbl(end-8:end)=[];
+            else
+                record.objects(obj).difficult=false;
+            end
+            if strcmp(lbl(max(end-4,1):end),'Trunc')
+                record.objects(obj).truncated=true;
+                lbl(end-4:end)=[];
+            else
+                record.objects(obj).truncated=false;
+            end
+            t=find(lbl>='A'&lbl<='Z');
+            t=t(t>=4);
+            if ~isempty(t)
+                record.objects(obj).view=lbl(t(1):end);
+                lbl(t(1):end)=[];
+            else
+                record.objects(obj).view='';                
+            end
+            record.objects(obj).class=lbl(4:end);
+
+	otherwise, %fprintf('Skipping: %s\n',line);
+      end;
+    end;
+  end;
+  fclose(fd);
+return
+
+function matchnum=match(line,matchstrs)
+  for i=1:length(matchstrs),
+    matched(i)=strncmp(line,matchstrs(i).str,matchstrs(i).matchlen);
+  end;
+  matchnum=find(matched);
+  if isempty(matchnum), matchnum=0; end;
+  if (length(matchnum)~=1), 
+    PASerrmsg('Multiple matches while parsing','');
+  end;
+return
+
+function s=initstrings
+  s(1).matchlen=14;
+  s(1).str='Image filename : %q';
+
+  s(2).matchlen=10;
+  s(2).str='Image size (X x Y x C) : %d x %d x %d';
+
+  s(3).matchlen=8;
+  s(3).str='Database : %q';
+
+  s(4).matchlen=8;
+  s(4).str='Bounding box for object %d %q (Xmin, Ymin) - (Xmax, Ymax) : (%d, %d) - (%d, %d)';
+
+  s(5).matchlen=7;
+  s(5).str='Polygon for object %d %q (X, Y)';
+
+  s(6).matchlen=5;
+  s(6).str='Pixel mask for object %d %q : %q';
+
+  s(7).matchlen=8;
+  s(7).str='Original label for object %d %q : %q';
+
+return

external/VOCdevkit/VOCcode/VOCap.m

@@ -0,0 +1,10 @@
+function ap = VOCap(rec,prec)
+
+mrec=[0 ; rec ; 1];
+mpre=[0 ; prec ; 0];
+for i=numel(mpre)-1:-1:1
+    mpre(i)=max(mpre(i),mpre(i+1));
+end
+i=find(mrec(2:end)~=mrec(1:end-1))+1;
+ap=sum((mrec(i)-mrec(i-1)).*mpre(i));
+

external/VOCdevkit/VOCcode/VOCevalaction.m

@@ -0,0 +1,59 @@
+function [rec,prec,ap] = VOCevalaction(VOCopts,id,cls,draw)
+
+% load test set
+[gtimg,gtobj,gt]=textread(sprintf(VOCopts.action.clsimgsetpath,cls,VOCopts.testset),'%s %d %d');
+
+% hash image/object ids
+gtid=cell(numel(gtimg),1);
+for i=1:numel(gtimg);
+    gtid{i}=sprintf('%s/%d',gtimg{i},gtobj(i));
+end
+hash=VOChash_init(gtid);
+
+% load results
+[img,obj,confidence]=textread(sprintf(VOCopts.action.respath,id,cls),'%s %d %f');
+
+% map results to ground truth objects
+out=ones(size(gt))*-inf;
+tic;
+for i=1:length(img)
+    % display progress
+    if toc>1
+        fprintf('%s: pr: %d/%d\n',cls,i,length(img));
+        drawnow;
+        tic;
+    end
+
+    % find ground truth object
+    k=sprintf('%s/%d',img{i},obj(i));
+    j=VOChash_lookup(hash,k);
+    if isempty(j)
+        error('unrecognized object "%s"',k);
+    elseif length(j)>1
+        error('multiple image "%s"',k);
+    else
+        out(j)=confidence(i);
+    end
+end
+
+% compute precision/recall
+
+[so,si]=sort(-out);
+tp=gt(si)>0;
+fp=gt(si)<0;
+
+fp=cumsum(fp);
+tp=cumsum(tp);
+rec=tp/sum(gt>0);
+prec=tp./(fp+tp);
+
+ap=VOCap(rec,prec);
+
+if draw
+    % plot precision/recall
+    plot(rec,prec,'-');
+    grid;
+    xlabel 'recall'
+    ylabel 'precision'
+    title(sprintf('class: %s, subset: %s, AP = %.3f',cls,VOCopts.testset,ap));
+end

external/VOCdevkit/VOCcode/VOCevalcls.m

@@ -0,0 +1,54 @@
+function [rec,prec,ap] = VOCevalcls(VOCopts,id,cls,draw)
+
+% load test set
+[gtids,gt]=textread(sprintf(VOCopts.clsimgsetpath,cls,VOCopts.testset),'%s %d');
+
+% hash image ids
+hash=VOChash_init(gtids);
+
+% load results
+[ids,confidence]=textread(sprintf(VOCopts.clsrespath,id,cls),'%s %f');
+
+% map results to ground truth images
+out=ones(size(gt))*-inf;
+tic;
+for i=1:length(ids)
+    % display progress
+    if toc>1
+        fprintf('%s: pr: %d/%d\n',cls,i,length(ids));
+        drawnow;
+        tic;
+    end
+
+    % find ground truth image
+    j=VOChash_lookup(hash,ids{i});
+    if isempty(j)
+        error('unrecognized image "%s"',ids{i});
+    elseif length(j)>1
+        error('multiple image "%s"',ids{i});
+    else
+        out(j)=confidence(i);
+    end
+end
+
+% compute precision/recall
+
+[so,si]=sort(-out);
+tp=gt(si)>0;
+fp=gt(si)<0;
+
+fp=cumsum(fp);
+tp=cumsum(tp);
+rec=tp/sum(gt>0);
+prec=tp./(fp+tp);
+
+ap=VOCap(rec,prec);
+
+if draw
+    % plot precision/recall
+    plot(rec,prec,'-');
+    grid;
+    xlabel 'recall'
+    ylabel 'precision'
+    title(sprintf('class: %s, subset: %s, AP = %.3f',cls,VOCopts.testset,ap));
+end