MCNN提出了适用于高密度人群的自适应高斯核:
笔者所理解的自适应高斯核函数:
%function:通过高斯核产生相应的密度矩阵
%parameter: im:输入图像,灰度图; points:标注的点[X Y],n*2的矩阵
function im_density = get_density_map_autogaussian(im,points)
im_density = zeros(size(im));
[h,w] = size(im_density);
if(isempty(points))
return;
end
%points为1行
if(length(points(:,1))==1)
x1 = max(1,min(w,round(points(1,1)))); %round:四舍五入,x1变成points(1,1)处的整数
y1 = max(1,min(h,round(points(1,2))));
im_density(y1,x1) = 255;
return;
end
for j = 1:length(points)
max_kernel = 65; %最大高斯核尺寸
normal_kernel = 35; %默认高斯核尺寸
beta =