// The constructor obtains the state information.
public locatePointThread( BaseTypes.viewport Vprt,Rectangle ScanArea,Bitmap Bmp,int AcceptanceThreshold,int radius, NeuralNetwork aan, locatePointThreadCallback callbackDelegate)
{
this.vprt = Vprt;
this.scanArea = ScanArea;
this.bmp = Bmp;
this.acceptanceThreshold = AcceptanceThreshold;
this.Radius=radius;
this.Ann=aan;
callback = callbackDelegate;
}
//train single neural network with given training set and parameters
private void trainNetwork(ArrayList trainingSet, ref NeuralNetwork Ann, double trainingRate, int trainingIterationsCount)
{
//set answers
double[] answerYes=new double[4]{1,1,1,1};
double[] answerNo=new double[4]{0,0,0,0};
int Iteration;
int index;
Random R = new Random();
for (Iteration=0; Iteration<trainingIterationsCount; Iteration++)
{
//random-pick training set index
index=(int)Math.Round((R.NextDouble() * ((32-1)-1)));
//get tranining sample from training set
double[] a = (double[])trainingSet[index];
//train network with set
if (index>15)
Ann.TrainNetwork(answerYes,a,trainingRate);
else
Ann.TrainNetwork(answerNo,a,trainingRate);
}
}
//train point in certain viewport (generate training set and train neural network)
private void trainPoint(BaseTypes.viewport vprt,Bitmap bmp, ref NeuralNetwork Ann, int hls, int ovs, int hlc, iActivationFunction af, double tr, int tic, int miw, int maw)
{
trainingSet=new ArrayList();
switch (vprt)
{
case BaseTypes.viewport.XY:
{
trainingSet=(ArrayList)(generateTrainingSet(BaseTypes.viewport.XY,bmp).Clone());
//create new neural network object
Ann = new NeuralNetwork((int)Math.Pow((xyRadius*2),2),hls, ovs,hlc,af);
//initialize weights
Ann.DrawWeights(miw, maw);
//train network
trainNetwork(trainingSet,ref Ann,tr,tic);
break;
}
case BaseTypes.viewport.XZ:
{
trainingSet=(ArrayList)(generateTrainingSet(BaseTypes.viewport.XZ,bmp).Clone());
//create new neural network object
Ann = new NeuralNetwork((int)Math.Pow((xzRadius*2),2),hls, ovs,hlc,af);
//initialize weights
Ann.DrawWeights(miw, maw);
//train network
trainNetwork(trainingSet,ref Ann,tr,tic);
break;
}
case BaseTypes.viewport.YZ:
{
trainingSet=(ArrayList)(generateTrainingSet(BaseTypes.viewport.YZ,bmp).Clone());
//create new neural network object
Ann = new NeuralNetwork((int)Math.Pow((yzRadius*2),2),hls, ovs,hlc,af);
//initialize weights
Ann.DrawWeights(miw, maw);
//train network
trainNetwork(trainingSet,ref Ann,tr,tic);
break;
}
}
}
public trackingPoint(string name, trackingPoint tp, Color col)
{
this.pColor = tp.pColor;
this.xyAnn = tp.xyAnn;
this.xyCoordX=tp.xyCoordX;
this.xyCoordY=tp.XyCoordY;
this.xyRadius=tp.xyRadius;
this.xyTrackPointImage=tp.xyTrackPointImage;
this.xzAnn = tp.xzAnn;
this.xzCoordX=tp.xzCoordX;
this.xzCoordZ=tp.xzCoordZ;
this.xzRadius=tp.xzRadius;
this.xzTrackPointImage=tp.xzTrackPointImage;
this.yzAnn = tp.yzAnn;
this.yzCoordZ=tp.yzCoordZ;
this.yzCoordY=tp.yzCoordY;
this.yzRadius=tp.yzRadius;
this.yzTrackPointImage=tp.yzTrackPointImage;
this.calculateWorldCoords();
this.pColor=col;
this.pName=name;
}