MATLAB编程混合高斯模型和改进的CV模型相结合的目标跟踪算法源码程序 - matlab算法设计

下载频道> 资源分类> matlab源码> 算法设计> MATLAB编程混合高斯模型和改进的CV模型相结合的目标跟踪算法源码程序

标题：MATLAB编程混合高斯模型和改进的CV模型相结合的目标跟踪算法源码程序
分享到：

所属分类: 算法设计资源类型：程序源码文件大小: 15.86 MB 上传时间: 2019-12-01 23:03:40 下载次数: 35 资源积分：1分提供者: jiqiren 20191201110453896

内容：
MATLAB编程混合高斯模型和改进的CV模型相结合的目标跟踪算法源码程序，能够准确的跟踪出车辆与行人

% This m-file implements the mixture of Gaussians algorithm for background

% subtraction. It may be used free of charge for any purpose (commercial

% or otherwise), as long as the author (Seth Benton) is acknowledged.

clear global;clear variables

close all; warning off

source = aviread('san_fran_traffic_30sec_QVGA_Cinepak.avi');

% ----------------------- frame size variables -----------------------

tic

fr = source(1).cdata; % read in 1st frame as background frame

fr_bw = rgb2gray(fr); % convert background to greyscale

fr_size = size(fr);

width = fr_size(2);

height = fr_size(1);

fg = zeros(height, width);

bg_bw = zeros(height, width);

% --------------------- mog variables -----------------------------------

C = 3; % number of gaussian components (typically 3-5)

M = 3; % number of background components

D = 2.5; % positive deviation threshold

alpha = 0.01; % learning rate (between 0 and 1) (from paper 0.01)

thresh = 0.25; % foreground threshold (0.25 or 0.75 in paper)

sd_init = 6; % initial standard deviation (for new components) var = 36 in paper

w = zeros(height,width,C); % initialize weights array

mean = zeros(height,width,C); % pixel means

sd = zeros(height,width,C); % pixel standard deviations

u_diff = zeros(height,width,C); % difference of each pixel from mean

p = alpha/(1/C); % initial p variable (used to update mean and sd)

rank = zeros(1,C); % rank of components (w/sd)

% --------------------- initialize component means and weights -----------

pixel_depth = 8; % 8-bit resolution

pixel_range = 2^pixel_depth -1; % pixel range (# of possible values)

for i=1:height

for j=1:width

for k=1:C

mean(i,j,k) = rand*pixel_range; % means random (0-255)

w(i,j,k) = 1/C; % weights uniformly dist

sd(i,j,k) = sd_init; % initialize to sd_init

end

%--------------------- process frames -----------------------------------

%for n =396:400%length(source)

%for n=455:460

for n=55:60

fr = source(n).cdata; % read in frame

fr_bw = rgb2gray(fr); % convert frame to grayscale

% calculate difference of pixel values from mean

for m=1:C

u_diff(:,:,m) = abs(double(fr_bw) - double(mean(:,:,m)));

end

% update gaussian components for each pixel

for i=1:height

for j=1:width

match = 0;

for k=1:C

if (abs(u_diff(i,j,k)) <= D*sd(i,j,k)) % pixel matches component

match = 1; % variable to signal component match

% update weights, mean, sd, p

w(i,j,k) = (1-alpha)*w(i,j,k) + alpha;

p = alpha/w(i,j,k);

mean(i,j,k) = (1-p)*mean(i,j,k) + p*double(fr_bw(i,j));

sd(i,j,k) = sqrt((1-p)*(sd(i,j,k)^2) + p*((double(fr_bw(i,j)) - mean(i,j,k)))^2);

else % pixel doesn't match component

w(i,j,k) = (1-alpha)*w(i,j,k); % weight slighly decreases

end

w(i,j,:) = w(i,j,:)./sum(w(i,j,:));

bg_bw(i,j)=0;

for k=1:C

bg_bw(i,j) = bg_bw(i,j)+ mean(i,j,k)*w(i,j,k);

end

% if no components match, create new component

if (match == 0)

[min_w, min_w_index] = min(w(i,j,:));

mean(i,j,min_w_index) = double(fr_bw(i,j));

sd(i,j,min_w_index) = sd_init;

end

rank = w(i,j,:)./sd(i,j,:); % calculate component rank

rank_ind = [1:1:C];

% sort rank values

for k=2:C

for m=1:(k-1)

if (rank(:,:,k) > rank(:,:,m))

% swap max values

rank_temp = rank(:,:,m);

rank(:,:,m) = rank(:,:,k);

rank(:,:,k) = rank_temp;

% swap max index values

rank_ind_temp = rank_ind(m);

rank_ind(m) = rank_ind(k);

rank_ind(k) = rank_ind_temp;

end

% calculate foreground

match = 0;

k=1;

fg(i,j) = 0;

while ((match == 0)&&(k<=M))

if (w(i,j,rank_ind(k)) >= thresh)

if (abs(u_diff(i,j,rank_ind(k))) <= D*sd(i,j,rank_ind(k)))

fg(i,j) = 0;

match = 1;

else

fg(i,j) = fr_bw(i,j);

end

k = k+1;

end

figure;

subplot(2,3,1),imshow(fr);

text(40,260,'(a1)输入图像');text(40,285,'(a1)Input Image');

subplot(2,3,2),imshow(uint8(bg_bw))

text(40,260,'(a2)背景模板');text(1,285,'(a2)Background Template');

subplot(2,3,3),imshow(uint8(fg))

text(40,260,'(a3)混合高斯算法');text(1,285,'(a3)Mixed Gaussian Model');

t=uint8(fg);

se=strel('line',3,0);

f=imclose(t,se);

f=imfill(f,'holes');

f=adpmedian(f,3);

f=bwmorph(f,'fill',100);

[Y,area]=falseRemoval(f);

subplot(2,3,4),imshow(Y);

text(40,275,'(a4)目标检测');text(40,299,'(a4)Target Detection ');

x=bwlabel(Y,8);

d=regionprops(x);

centroid = d.Centroid;

cc = centroid(1)+40;

cr = centroid(2)-5;

%cc = centroid(1);

%cr = centroid(2);

[MR,MC,Dim] = size(fr);

R=[[0.2845,0.0045]',[0.0045,0.0455]'];

H=[[1,0]',[0,1]',[0,0]',[0,0]'];

Q=0.01*eye(4);

P = 100*eye(4);

dt=3;

A=[[1,0,0,0]',[0,1,0,0]',[dt,0,1,0]',[0,dt,0,1]'];

g = 1; % pixels^2/time step

Bu = [0,0,0,g]';

kfinit=0;

x=zeros(100,4);

if flag==0

continue

end

hold on

% Kalman update

if kfinit==0

xp = [MC/2,MR/2,0,0]'

else

xp=A*x(i-1,:)' + Bu

end

kfinit=1;

PP = A*P*A' + Q

K = PP*H'*inv(H*PP*H'+R)

x(i,:) = (xp + K*([cc,cr]' - H*xp))';

P = (eye(4)-K*H)*PP

hold on;

% Img=imread('vessel3.bmp');

%Img=imnoise(fr,'salt & pepper',0.2);

Img=double(fr(:,:,1));

% get the size

[nrow,ncol] =size(Img)

ic= cr;

jc= cc;

r=40;

initialLSF = sdf2circle(nrow,ncol,ic,jc,r);

phi=initialLSF;

subplot(2,3,5),contour(phi,[0 0],'b','LineWidth',2);

text(40,275,'(a5)初始化曲线');text(40,295,'(a5)Initialization Curve');

iterNum =50;

lambda1 = 1.0;

lambda2 = 1.0;

nu = 0.004*255*255;

%timestep =10.0;

timestep =10.5;

mu = 1;

epsilon = 1.5;

sigma=5.0;

K=fspecial('gaussian',round(2*sigma)*2+1,sigma); % Gaussian kernel

KI=conv2(Img,K,'same');

KONE=conv2(ones(size(Img)),K,'same');

sigma=0.5; % scale parameter in Gaussian kernel for smoothing.

G=fspecial('gaussian',2,sigma);

Img_smooth=conv2(Img,G,'same'); % smooth image by Gaussiin convolution

[Ix,Iy]=gradient(Img);

f=Ix.^2+Iy.^2;

k=0.02.*max(Ix,Iy);

if f<=k

g=1;

else

g=1./(1+f-k);

end

imagesc(Img,[0 255]);colormap(gray)

hold on;

subplot(2,3,5),contour(phi,[0 0],'b','LineWidth',2);

text(40,275,'(a5)初始化曲线');text(40,295,'(a5)Initialization Curve');

subplot(2,3,6),contour(phi,[0 0],'b','LineWidth',2);

% start level set evolution

time = cputime;

for n=1:iterNum

numIter=1;

%level set evolution.

phi=EVOL_LBF(phi,g,Img,K,KI,KONE,nu,timestep,mu,lambda1,lambda2,epsilon,numIter);

if mod(n,10)==0

pause(0.001);

imagesc(Img, [0, 255]);colormap(gray);hold on; axis off;

subplot(2,3,6), contour(phi,[0 0],'b','LineWidth',2);

text(40,275,'(a6)目标追踪');text(40,295,'(a6)Target Tracking');

%iterNum=[num2str(n), ' iterations'];

%title(iterNum);

hold off;

end

totaltime = cputime - time;

imagesc(Img, [0, 255]);colormap(gray);hold on; axis off;

subplot(2,3,6),contour(phi,[0 0],'b','LineWidth',2);

text(40,275,'(a6)目标追踪');text(40,295,'(a6)Target Tracking');

end

toc

文件列表（点击上边下载按钮，如果是垃圾文件请在下面评价差评或者投诉）:

EVOL_LBF.m
Main_BG_GM.m
falseRemoval.m
san_fran_traffic_30sec_QVGA_Cinepak.avi
sdf2circle.m

关键词： MATLAB 编程 混合 高斯 模型 改进 CV模型 源码 程序

matlab源码下载排行

回到顶部

友情链接

matlab源码网站源码编程语言网络编程手机通讯编程 KUNAG 官网 KUNAG 电商更多

: 联系方式| 版权声明| 招聘信息| 广告服务| 银行汇款| 法律顾问| 兼职技术| 付款方式| 关于我们|; 网站客服程序员兼职招聘 411241577@qq.com; 沪ICP备19040327号-3; 公安备案号：沪公网安备 31011802003874号; 库纳格流体控制系统（上海）有限公司版权所有; Copyright © 1999-2014, GUSUCODE.COM, All Rights Reserved

关键词： MATLAB 编程 混合 高斯 模型 改进 CV模型 源码 程序

相关推荐

matlab源码下载排行

友情链接

关键词： MATLAB 编程混合高斯模型改进 CV模型源码程序