OpenCV学习——物体跟踪的粒子滤波算法实现之计算选定区域直方图

/*
Computes a reference histogram for each of the object regions defined by
the user

@param frame video frame in which to compute histograms; should have been
converted to hsv using bgr2hsv in observation.h
@param regions regions of \a frame over which histograms should be computed
@param n number of regions in \a regions
@param export if TRUE, object region images are exported

@return Returns an \a n element array of normalized histograms corresponding
to regions of \a frame specified in \a regions.
*/
histogram** compute_ref_histos( IplImage* frame, CvRect* regions, int n )
{
histogram** histos = malloc( n * sizeof( histogram* ) );
IplImage* tmp;
int i;

/* extract each region from frame and compute its histogram */
for( i = 0; i < n; i++ )
{
cvSetImageROI( frame, regions[i] );//set the region of interest
tmp = cvCreateImage( cvGetSize( frame ), IPL_DEPTH_32F, 3 );
cvCopy( frame, tmp, NULL );
cvResetImageROI( frame );//free the ROI
histos[i] = calc_histogram( &tmp, 1 );//calculate the hisrogram
normalize_histogram( histos[i] );//Normalizes a histogram so all bins sum to 1.0
cvReleaseImage( &tmp );
}

return histos;
}

程 序中先设置了一个类型为histogram的指向指针的指针，是histogram指针数组的指针，这个数组是多个选定区域的直方图数据存放的位置。然后 对于每一个用户指定的区域，在第一帧中都进行了ROI区域设置，通过对ROI区域的设置取出选定区域，交给函数calc_histogram计算出直方 图，并使用normalize_histogram对直方图进行归一化。
计算直方图的函数详解如下：
/*
Calculates a cumulative histogram as defined above for a given array
of images

@param img an array of images over which to compute a cumulative histogram;
each must have been converted to HSV colorspace using bgr2hsv()
@param n the number of images in imgs

@return Returns an un-normalized HSV histogram for \a imgs
*/
histogram* calc_histogram( IplImage** imgs, int n )
{
IplImage* img;
histogram* histo;
IplImage* h, * s, * v;
float* hist;
int i, r, c, bin;

histo = malloc( sizeof(histogram) );
histo->n = NH*NS + NV;
hist = histo->histo;
memset( hist, 0, histo->n * sizeof(float) );

for( i = 0; i < n; i++ )
{
/* extract individual HSV planes from image */
img = imgs[i];
h = cvCreateImage( cvGetSize(img), IPL_DEPTH_32F, 1 );
s = cvCreateImage( cvGetSize(img), IPL_DEPTH_32F, 1 );
v = cvCreateImage( cvGetSize(img), IPL_DEPTH_32F, 1 );
cvCvtPixToPlane( img, h, s, v, NULL );

/* increment appropriate histogram bin for each pixel */
for( r = 0; r < img->height; r++ )
for( c = 0; c < img->width; c++ )
{
bin = histo_bin( pixval32f( h, r, c ),
pixval32f( s, r, c ),
pixval32f( v, r, c ) );
hist[bin] += 1;
}
cvReleaseImage( &h );
cvReleaseImage( &s );
cvReleaseImage( &v );
}
return histo;
}


这个函数将h、s、 v分别取出，然后以从上到下，从左到右的方式遍历以函数histo_bin的评判规则放入相应的bin中（很形象的）。函数histo_bin的评判规则详见下图：


｜－－－－｜－－－－｜－－－－｜。。。。｜－－－－｜－－－－－－｜－－－－－－｜。。。。｜－－－－－－－｜

1NH 2NH 3NH NS＊NH NS＊NH＋1 NS*NH+2 NS＊NH＋NV