|
Hi All,
I am writing a program to download some data off a piece of hardware. My thinking was have an array fill it. The data is in the form of strings rather than ints (which have done this with in the past) my question is strings are bigger than ints so will this cause issues with overflow and what is the correct way of handling groups of strings??
Glenn
|
|
|
|
|
First of all, why an array? Why not a List of strings?
Second, are the strings unique or are they just a well defined list that you could get some combination of? If it's a well known list, just assign an enumeration to the strings and return a list of those enumerations.
Alternatively, you could write a slightly more complex algorithm and use a Dictionary to keep the string, and a list of indexes where that string occur - and then decode this at the client end.
|
|
|
|
|
I have only really looked at List from a distance can you recommend a good tutorial?
I just need to get the strings and possibly check them and save them.
Glenn
|
|
|
|
|
Here you go. Defining a list of strings:
List<string> myStrings = new List<string>(); Doing the same and setting the initial size to 100 elements
List<string> myStrings = new List<string>(100); Adding to the string
myStrings.Add("A string");That's pretty much it as far as you need to get started.
|
|
|
|
|
Really that simple? (something somewhere is going to go bang!)
Thanks
Glenn!
|
|
|
|
|
Really that simple. Of course, there's a lot more you can do with the list, but that's enough to get you going.
|
|
|
|
|
Cool, I have also found
<a href=>"http://www.codeproject.com/Articles/38447/Generic-List-C">Generic List (C#)</a>
Looks like that is my afternoon sorted!
Glenn
|
|
|
|
|
It can insert multiple values or characters in your program. Array of string is the best way to insert multiple character to take at a time with the help of strings. Most of string start from zero. Three kind of strings are there : one pair string,two pair string and multiple pair string.
|
|
|
|
|
Are you really sure you meant to reply to me? The OP doesn't get notified if you post an answer to my posts.
|
|
|
|
|
Thanks for the Help! I now have it getting the data tomorrow I can work on it further,but now have the bones.
Glenn
|
|
|
|
|
You're welcome. I look forward to finding out how you get on.
|
|
|
|
|
You are not the only one, it would easier if I had more direction than oh it work like X when X is not fully tested and the board you are writing the code for does not exist yet, but to keep the powers that be happy (Gannt charts running) "The Windows Interface Code Must Be Started:". Will let you know!
Glenn
(Dilbert anyone??)
|
|
|
|
|
Yes a List, or a Queue if you want to have one thread adding values and another processing them. 
glennPattonWork wrote: strings rather than ints
If they are ints that have been stringified, then why not Parse them and then add them to the collection?
|
|
|
|
|
Good, These are strings, I meant I had used an integer array to store the data as it came in. I was thinking that as Strings are bigger in size I didn't want to slow everything down by trying to handle a load of them as an array, (seemed to me like having one huge box containing smaller boxes rather unwieldy!)
Glenn
|
|
|
|
|
The alternative, as noted in this part of the thread, is to use a Queue so you could remove items when you are finished processing them - this helps to keep things down to a more managable size.
|
|
|
|
|
While text (strings) may be a good way to transfer information between systems, it is not the recommended way to store data in memory. So my approach would be slightly different, I'd have:
- a textual representation of the data, as an example X123Y456E would be a point with X and Y coordinates (E stands for a terminator, think newline character);
- a class that holds an instance of data, in the example:
public class MyPoint {
public int X;
public int Y;
}
BTW: I prefer a class over a struct to avoid all kinds of problems including boxing/unboxing.
- some container that holds all the data, this could be List<MyPoint> myCollectionOfPoints in the example.
- a method to receive textual data, convert it on the spot, and store it; it might look like:
public void ReceiveMyPoint() {
string line=mySerialPort.ReadLine();
... here comes input validation and parsing, resulting in actual values:
int x=...;
int y=...;
myCollectionOfPoints.Add(new MyPoint(x,y));
}
- a thread to consume all incoming data, basically a loop calling ReceiveMyPoint() all the time. I don't use the DataReceived event here, as that does not synchronize with incoming text lines, it fires randomly when "some data" is available, which may well be a partial line of text.
The net result is your interface is textual, the data is in meaningful types (two ints in the example), conversion is not a separate step, and no storage space gets wasted.
Note: you must program defensively when receiving data from another system, as it will go wrong sooner or later, with a bad conenction, some missing characters, a noisy line, whatever. Therefore validation is important; even the simplest checksum or CRC added to each message would prove valuable.
|
|
|
|
|
Great thanks for that, can you recommend a reference for this type of data handling (or really any data handling would be useful) It's just I am tasked with writing an application to interface to a board that does exist (yet!) "it will do it like the X board, you already written the software for that". I'm looking at this as a chance to increase my Windows knowledge!
Glenn
|
|
|
|
|
Sorry, no reference, just my own experience with peripherals and embedded systems.
|
|
|
|
|
Ah well google & MSDN, I did look at something on the code project that confused me! (link earlier)
Glenn
|
|
|
|
|
Thanks for the Help! I now have it getting the data tomorrow I can work on it further,but now have the bones.
Glenn
|
|
|
|
|
using System;
using System.Collections.Generic;
using System.Text;
using System.Drawing;
using System.Collections;
using System.Windows.Forms;
class SIFT
{ static double initDev = 1.6;
static public int OctavesCount = 2;
static public int scalesPerOctave = 4;
static double minDoG = 0.01;
static public double norm;
static double edgeRatio = 10;
public static double[][,] BuildGaussianBlurPyramid(Bitmap image)
{ int ind=1;
int imgCount = scalesPerOctave * OctavesCount;
double deviation = initDev;
double[][,] imgMatrix=new double[imgCount][,];
imgMatrix[0]=new double[image.Width,image.Height];
imgMatrix[0]=ImageProcessing.BitmapToGrayscaleMatrix(image);
for (int i = 0; i < OctavesCount; i++){
for (int j = 1; j < scalesPerOctave; j++){
imgMatrix[ind]=ImageProcessing.GaussianBlurBWMat(imgMatrix[ind-1], deviation);
deviation *= 2;
ind++;
}
if (ind<imgCount-1)
imgMatrix[ind] = ImageProcessing.SubSample(imgMatrix[ind-2]);
deviation /= 3.2;
ind++;
}
return imgMatrix;
}
public static double[][,] BuildDoGPyramid(double[][,] gaussianPyr)
{ int ind = 0;
double[][,] resDoG = new double[(scalesPerOctave - 1) * OctavesCount][,];
for (int i = 0; i < gaussianPyr.GetLength(0) - 1; i += 1){
if ((i + 1) % (scalesPerOctave) == 0){
continue;
}
resDoG[ind] = ImageProcessing.CalculateDoGMatrix(gaussianPyr[i], gaussianPyr[i + 1]);
ind++;
}
return resDoG;
}
public static ArrayList FindKeypoints(double[][,] imgMatrixPyr)
{ ArrayList KpL = new ArrayList();
double[][][,] imgMatrix = new double[2][][,];
norm = 3.0 / (initDev * 2);
int DoGCount = (scalesPerOctave - 1) * OctavesCount;
imgMatrix[0] = new double[3][,];
imgMatrix[1] = new double[3][,];
int pyrL = 0;
int pyrIm = 0;
for (int i = 0; i < DoGCount; i++){
if (i == 3){
pyrL++;
pyrIm = 0;
}
imgMatrix[pyrL][pyrIm] = imgMatrixPyr[i];
pyrIm++;
}
int min = 1, max = 1;
for (int l = 0; l < imgMatrix.GetLength(0); l++){
for (int y = 1; y < imgMatrix[l][1].GetLength(1) - 1; y++)
for (int x = 1; x < imgMatrix[l][1].GetLength(0) - 1; x++){
double point = imgMatrix[l][1][x, y];
if (Math.Abs(point) <= minDoG)
continue;
for (int i = 0; i < imgMatrix[l].GetLength(0); i++){
if (max == 1 & imgMatrix[l][i][x - 1, y - 1] < point & imgMatrix[l][i][x - 1, y] < point &
imgMatrix[l][i][x, y - 1] < point & imgMatrix[l][i][x, y] <= point & imgMatrix[l][i][x + 1, y + 1] < point &
imgMatrix[l][i][x + 1, y] < point & imgMatrix[l][i][x, y + 1] < point & imgMatrix[l][i][x - 1, y + 1] < point &
imgMatrix[l][i][x + 1, y - 1] < point){
max = 1;
}
else max = 0;
if (min == 1 & imgMatrix[l][i][x - 1, y - 1] > point & imgMatrix[l][i][x - 1, y] > point &
imgMatrix[l][i][x, y - 1] > point & imgMatrix[l][i][x, y] >= point & imgMatrix[l][i][x + 1, y + 1] > point &
imgMatrix[l][i][x + 1, y] > point & imgMatrix[l][i][x, y + 1] > point & imgMatrix[l][i][x - 1, y + 1] > point &
imgMatrix[l][i][x + 1, y - 1] > point){
min = 1; }
else min = 0;
}
if (max == 1 || min == 1){
Keypoint kp = new Keypoint();
kp.x = x;
kp.y = y;
kp.value = point;
kp.layer = l;
KpL.Add(kp); }
min = 1; max = 1;
}
}
return KpL;
}
public static ArrayList KeypointLocalization(ArrayList initKpList, double[][,] DoGMatrix, int edgeRatio)
{ Keypoint initKp;
ArrayList retKp = new ArrayList();
double Dxx, Dyy, Dxy, Trace, Det;
double r = ((edgeRatio + 1) * (edgeRatio + 1)) / 2;
for (int i = 0; i < initKpList.Count; i++){
initKp = (Keypoint)initKpList[i];
int l = initKp.layer == 0 ? 1 : 4;
if (initKp.x <= 0 || initKp.y <= 0 ||
initKp.x >= DoGMatrix[l].GetLength(0) - 1
|| initKp.y >= DoGMatrix[l].GetLength(0) - 1)
continue;
Dxx = DoGMatrix[l][initKp.x + 1, initKp.y]
+ DoGMatrix[l][initKp.x - 1, initKp.y]
- 2.0 * DoGMatrix[l][initKp.x, initKp.y];
Dyy = DoGMatrix[l][initKp.x, initKp.y + 1]
+ DoGMatrix[l][initKp.x, initKp.y - 1]
- 2.0 * DoGMatrix[l][initKp.x, initKp.y];
Dxy = 0.25 * ((DoGMatrix[l][initKp.x + 1, initKp.y + 1]
- DoGMatrix[l][initKp.x + 1, initKp.y - 1]) -
(DoGMatrix[l][initKp.x - 1, initKp.y + 1]
- DoGMatrix[l][initKp.x - 1, initKp.y - 1]));
Trace = Dxx + Dyy;
Det = Dxx * Dyy - (Dxy * Dxy);
if ((Trace * Trace) / Det > r)
continue;
else
retKp.Add(initKp);
}
return retKp;
}
public static ArrayList AssignOrientations(ArrayList finKpList, double[][,] blurredMatrix)
{ Keypoint finKp;
ArrayList orKp=new ArrayList();
double binVal = 2 * Math.PI / 36;
for (int i = 0; i < finKpList.Count; i++){
finKp = (Keypoint)finKpList[i];
finKp.scale = initDev*(finKp.layer + 1);
double[] histBin = new double[36];
int kpReg=(int)(1.5*finKp.scale/2+0.5);
double SigmaFact=2*2.25*finKp.scale*finKp.scale;
int layer=finKp.layer==0?1:5;
int regXSt=finKp.x-kpReg<1?1:finKp.x-kpReg;
int regXEnd = finKp.x + kpReg > blurredMatrix[layer].GetLength(0) ? blurredMatrix[layer].GetLength(0) : finKp.x + kpReg;
int regYSt = finKp.y - kpReg < 1 ? 1 : finKp.y - kpReg;
int regYEnd = finKp.y + kpReg > blurredMatrix[layer].GetLength(1) ? blurredMatrix[layer].GetLength(1) : finKp.y + kpReg;
for (int y=regYSt; y<regYEnd; y++)
for (int x=regXSt; x<regXEnd; x++){
double gaussianWight = Math.Exp(-(Math.Pow(x - finKp.x, 2) + Math.Pow(y - finKp.y, 2) / SigmaFact));
double portInHist = (CalMagnitudeAndDirection(x,y, blurredMatrix[layer]).direction + Math.PI) / (2 * Math.PI);
int ind = (int)(portInHist * 36 == 36 ? 0 : portInHist * 36);
histBin[ind]+=CalMagnitudeAndDirection(x,y,blurredMatrix[layer]).magnitude*gaussianWight;
}
double max = 0.0;
int maxBin = 0;
for (int bi = 0; bi < histBin.GetLength(0); ++bi){
if (histBin[bi] > max){
max = histBin[bi];
maxBin = bi; }
}
max = maxBin * binVal - Math.PI;
max=max<-Math.PI?2*Math.PI+max:max;
max = max > Math.PI ? max - 2 * Math.PI : max;
finKp.orientation = max;
orKp.Add(finKp);
}
return orKp;
}
static KpOrientPar CalMagnitudeAndDirection(int x, int y, double[,] blurredMatrix)
{ KpOrientPar kpO=new KpOrientPar();
kpO.magnitude = Math.Sqrt (Math.Pow (blurredMatrix[x + 1, y] - blurredMatrix[x - 1, y], 2.0) +
Math.Pow (blurredMatrix[x, y + 1] - blurredMatrix[x, y - 1], 2.0));
kpO.direction = Math.Atan2(blurredMatrix[x, y + 1] - blurredMatrix[x, y - 1],
blurredMatrix[x + 1, y] - blurredMatrix[x - 1, y]);
return kpO;
}
public static ArrayList CreateDescriptor(ArrayList finKpList, double[][,] blurredMatrix)
{ int kpReg = 16;
Keypoint finKp;
ArrayList descKp=new ArrayList();
double SigmaFact = 2*(kpReg / 2) * (kpReg / 2);
for (int kpi = 0; kpi < finKpList.Count; kpi++){
finKp = (Keypoint)finKpList[kpi];
int regXSt = finKp.x - kpReg < 1 ? 1 : finKp.x - kpReg;
int regYSt = finKp.y - kpReg < 1 ? 1 : finKp.y - kpReg;
int regXEnd = regXSt + 4;
int regYEnd = regXSt + 4;
double[,][] desc = new double[4, 4][];
for (int jj = 0; jj < 4; jj++)
for (int ii = 0; ii < 4; ii++ )
desc[ii,jj] = new double[8];
int layer = finKp.layer == 0 ? 1 : 5;
for (int i = 0; i <= 3; i++)
for (int j =0 ; j <= 3; j++)
for (int xi = regXSt; xi < regXEnd; xi++)
for (int yi = regYSt; yi < regYEnd; yi++){
int x =xi+j*4 >= blurredMatrix[layer].GetLength(0)-1 ? blurredMatrix[layer].GetLength(0)-2 : xi+j*4;
int y = yi+i*4 >= blurredMatrix[layer].GetLength(1)-1 ? blurredMatrix[layer].GetLength(1)-2 : yi+i*4;
double yRot = Math.Sin(-finKp.orientation) * (x - finKp.x) +
Math.Cos(-finKp.orientation) * (y - finKp.y);
double xRot = Math.Cos(-finKp.orientation) * (x - finKp.x) -
Math.Sin(-finKp.orientation) * (y - finKp.y);
double gaussianWight = Math.Exp(-(Math.Pow(xRot, 2) + Math.Pow(yRot, 2) / SigmaFact));
double direction = CalMagnitudeAndDirection(x, y, blurredMatrix[layer]).direction - finKp.orientation;
if (direction < 0)
direction += 2.0 * Math.PI;
else if (direction > 2.0 * Math.PI)
direction -= 2.0 * Math.PI;
double portInHist = direction / (2 * Math.PI);
int ind = (int)(portInHist * 8 == 8 ? 0 : portInHist * 8);
desc[i, j][ind] += CalMagnitudeAndDirection(x, y, blurredMatrix[layer]).magnitude * gaussianWight;
}
finKp.descriptor=desc;
descKp.Add(finKp);
}
return descKp;
}
}
class KpOrientPar
{
public double magnitude;
public double direction;
}
|
|
|
|
|
help me to debug this program ..thanx alot
|
|
|
|
|
You want to know what this code do?
|
|
|
|
|
In the code that calls the method you are getting an exception in, put a breakpoint on the line that calls the method (you can do this by pressing F9). Run your program in debug mode and when the program hits the breakpoint, it will pause execution. At this point, press F11 to step into the method. Check that the parameters that you have passed in are what you would expect. Now, use the step over command (F10) to step over individual code lines, and use step into (F11) to inspect methods that are of interest to you.
Check the values of variables as you progress to determine where the calculation goes wrong (if that's what your problem is), and to check that the right value gets allocated to the right place. This is going to require a lot of patience on your part, so take your time. It also means that you are going to have to be aware of what values you should get at what point.
And that, in a nutshell, is how you debug it.
|
|
|
|
|
Sorry for the inconvenience
please try the program and debug the error then paste it here
thanx
|
|
|
|
|
General 
News 
Suggestion 
Question 
Bug 
Answer 
Joke 
Praise 
Rant 
Admin 
Submit an article or tip
