OpenCV学习——物体跟踪的粒子滤波算法实现之初始化粒子集

最新推荐文章于 2023-05-16 19:59:52 发布

最新推荐文章于 2023-05-16 19:59:52 发布 · 257 阅读

文章标签：

#算法 #XP #QQ #J#

本文介绍了一种粒子分布初始化算法，该算法根据指定位置创建粒子集合。通过输入玩家位置区域和直方图描述，能够创建指定数量的粒子，并将它们均匀分布在各个区域的中心。

www.diy567.com累了，去上面休息一下下,QQ空间，美文，非主流，网络日记，搞笑短信，祝福短信，热门短信，有意思啊

/*
Creates an initial distribution of particles at specified locations

@param regions an array of regions describing player locations around
which particles are to be sampled
@param histos array of histograms describing regions in \a regions
@param n the number of regions in \a regions
@param p the total number of particles to be assigned

@return Returns an array of \a p particles sampled from around regions in
\a regions
*/
particle* init_distribution( CvRect* regions, histogram** histos, int n, int p)
{
particle* particles;
int np;
float x, y;
int i, j, width, height, k = 0;

particles = malloc( p * sizeof( particle ) );
np = p / n;

/* create particles at the centers of each of n regions */
for( i = 0; i < n; i++ )
{
width = regions[i].width;
height = regions[i].height;
x = regions[i].x + width / 2;
y = regions[i].y + height / 2;
for( j = 0; j < np; j++ )
{
particles[k].x0 = particles[k].xp = particles[k].x = x;
particles[k].y0 = particles[k].yp = particles[k].y = y;
particles[k].sp = particles[k].s = 1.0;
particles[k].width = width;
particles[k].height = height;
particles[k].histo = histos[i];
particles[k++].w = 0;
}
}

/* make sure to create exactly p particles */
i = 0;
while( k < p )
{
width = regions[i].width;
height = regions[i].height;
x = regions[i].x + width / 2;
y = regions[i].y + height / 2;
particles[k].x0 = particles[k].xp = particles[k].x = x;
particles[k].y0 = particles[k].yp = particles[k].y = y;
particles[k].sp = particles[k].s = 1.0;
particles[k].width = width;
particles[k].height = height;
particles[k].histo = histos[i];
particles[k++].w = 0;
i = ( i + 1 ) % n;
}

return particles;
}

程序中的变量np是指若有多个区域n，则一个区域内的粒子数为p/n，这样粒子的总数为p。然后程序对每个区域（n个）中p/n个粒子进行初始化，三个位置坐标都为选定区域的中点，比例都为1，宽度和高度为选定区域的高度。然后又跑了个循环确定p个粒子被初始化。