computer vision - train Cascade ObjectDetector matlab -
i'm asking how can'i use traincascadeobjectdetector while create positive smples structre composed of filename , bonding boxes cordinates. hase negative exemple images file. when lnche function flow
traincascadeobjectdetector('newdetector.xml', str, negativefolder, 'falsealarmrate', 0.2, 'numcascadestages', 5);
i have error:
error using traincascadeobjectdetector>parseinputs (line 306) argument 'positive_instances' failed validation error: cannot find struct field 'imagefilename' in positive_instances. error in traincascadeobjectdetector (line 161) parser = parseinputs(varargin{:});
as error says, str not contain field called imagefilename
, should field image files are. quoting matlab documentation:
positive_instances array of structs information positive instances. struct fields are: imagefilename - string specifies image name. image can true color, grayscale, or indexed, in of formats supported imread.
objectboundingboxes - m-by-4 matrix of [x y width height] bounding boxes specifying object locations.
so, str
argument should array of structs information, i.e (file1 has 3 boxes, file2 2 , file3 4):
str = struct('imagefilename',{'file1path', 'file2path', 'file3path'},... 'objectboundingboxes',{[xbox1 ybox1 w1 h1;xbox2 ybox2 w2 h2;xbox3 ybox3 w3 h3]... [xbox1 ybox1 w1 h1;xbox2 ybox2 w2 h2],... [xbox1 ybox1 w1 h1;xbox2 ybox2 w2 h2;xbox3 ybox3 w3 h3,xbox4 ybox4 w4 h4]});
or other way want declare it. sure input files in format.
Comments
Post a Comment