可以使用哪些图像处理技术来实现检测以下图像中显示的圣诞树的应用程序?
我正在寻找解决方案，将工作在所有这些图像。因此，需要训练haar级联分类器或模板匹配的方法不是很有趣。
我正在寻找可以用任何编程语言编写的东西，只要它只使用开源技术。解决方案必须使用在此问题上共享的图像进行测试。有6个输入图像，答案应该显示处理每个图像的结果。最后，对于每个输出图像，必须在检测到的树周围绘制红线。
您将如何通过编程来检测这些图像中的树木呢?
编辑注意:我编辑这篇文章是为了(I)按照要求分别处理每个树图像，(ii)同时考虑物体亮度和形状，以提高结果的质量。
下面是一种考虑到物体亮度和形状的方法。换句话说，它寻找的是具有三角形形状和显著亮度的物体。它是用Java语言实现的，使用Marvin图像处理框架。
第一步是颜色阈值。这里的目标是集中分析具有显著亮度的物体。
输出图片:
源代码:
public class ChristmasTree {
private MarvinImagePlugin fill = MarvinPluginLoader.loadImagePlugin("org.marvinproject.image.fill.boundaryFill");
private MarvinImagePlugin threshold = MarvinPluginLoader.loadImagePlugin("org.marvinproject.image.color.thresholding");
private MarvinImagePlugin invert = MarvinPluginLoader.loadImagePlugin("org.marvinproject.image.color.invert");
private MarvinImagePlugin dilation = MarvinPluginLoader.loadImagePlugin("org.marvinproject.image.morphological.dilation");
public ChristmasTree(){
MarvinImage tree;
// Iterate each image
for(int i=1; i<=6; i++){
tree = MarvinImageIO.loadImage("./res/trees/tree"+i+".png");
// 1. Threshold
threshold.setAttribute("threshold", 200);
threshold.process(tree.clone(), tree);
}
}
public static void main(String[] args) {
new ChristmasTree();
}
}
在第二步中，图像中最亮的点被放大以形成形状。这一过程的结果是具有显著亮度的物体的可能形状。应用洪水填充分割，断开的形状被检测。
输出图片:
源代码:
public class ChristmasTree {
private MarvinImagePlugin fill = MarvinPluginLoader.loadImagePlugin("org.marvinproject.image.fill.boundaryFill");
private MarvinImagePlugin threshold = MarvinPluginLoader.loadImagePlugin("org.marvinproject.image.color.thresholding");
private MarvinImagePlugin invert = MarvinPluginLoader.loadImagePlugin("org.marvinproject.image.color.invert");
private MarvinImagePlugin dilation = MarvinPluginLoader.loadImagePlugin("org.marvinproject.image.morphological.dilation");
public ChristmasTree(){
MarvinImage tree;
// Iterate each image
for(int i=1; i<=6; i++){
tree = MarvinImageIO.loadImage("./res/trees/tree"+i+".png");
// 1. Threshold
threshold.setAttribute("threshold", 200);
threshold.process(tree.clone(), tree);
// 2. Dilate
invert.process(tree.clone(), tree);
tree = MarvinColorModelConverter.rgbToBinary(tree, 127);
MarvinImageIO.saveImage(tree, "./res/trees/new/tree_"+i+"threshold.png");
dilation.setAttribute("matrix", MarvinMath.getTrueMatrix(50, 50));
dilation.process(tree.clone(), tree);
MarvinImageIO.saveImage(tree, "./res/trees/new/tree_"+1+"_dilation.png");
tree = MarvinColorModelConverter.binaryToRgb(tree);
// 3. Segment shapes
MarvinImage trees2 = tree.clone();
fill(tree, trees2);
MarvinImageIO.saveImage(trees2, "./res/trees/new/tree_"+i+"_fill.png");
}
private void fill(MarvinImage imageIn, MarvinImage imageOut){
boolean found;
int color= 0xFFFF0000;
while(true){
found=false;
Outerloop:
for(int y=0; y<imageIn.getHeight(); y++){
for(int x=0; x<imageIn.getWidth(); x++){
if(imageOut.getIntComponent0(x, y) == 0){
fill.setAttribute("x", x);
fill.setAttribute("y", y);
fill.setAttribute("color", color);
fill.setAttribute("threshold", 120);
fill.process(imageIn, imageOut);
color = newColor(color);
found = true;
break Outerloop;
}
}
}
if(!found){
break;
}
}
}
private int newColor(int color){
int red = (color & 0x00FF0000) >> 16;
int green = (color & 0x0000FF00) >> 8;
int blue = (color & 0x000000FF);
if(red <= green && red <= blue){
red+=5;
}
else if(green <= red && green <= blue){
green+=5;
}
else{
blue+=5;
}
return 0xFF000000 + (red << 16) + (green << 8) + blue;
}
public static void main(String[] args) {
new ChristmasTree();
}
}
如输出图像所示，检测到多个形状。在这个问题中，图像中只有几个亮点。但是，实现这种方法是为了处理更复杂的场景。
In the next step each shape is analyzed. A simple algorithm detects shapes with a pattern similar to a triangle. The algorithm analyze the object shape line by line. If the center of the mass of each shape line is almost the same (given a threshold) and mass increase as y increase, the object has a triangle-like shape. The mass of the shape line is the number of pixels in that line that belongs to the shape. Imagine you slice the object horizontally and analyze each horizontal segment. If they are centralized to each other and the length increase from the first segment to last one in a linear pattern, you probably has an object that resembles a triangle.
源代码:
private int[] detectTrees(MarvinImage image){
HashSet<Integer> analysed = new HashSet<Integer>();
boolean found;
while(true){
found = false;
for(int y=0; y<image.getHeight(); y++){
for(int x=0; x<image.getWidth(); x++){
int color = image.getIntColor(x, y);
if(!analysed.contains(color)){
if(isTree(image, color)){
return getObjectRect(image, color);
}
analysed.add(color);
found=true;
}
}
}
if(!found){
break;
}
}
return null;
}
private boolean isTree(MarvinImage image, int color){
int mass[][] = new int[image.getHeight()][2];
int yStart=-1;
int xStart=-1;
for(int y=0; y<image.getHeight(); y++){
int mc = 0;
int xs=-1;
int xe=-1;
for(int x=0; x<image.getWidth(); x++){
if(image.getIntColor(x, y) == color){
mc++;
if(yStart == -1){
yStart=y;
xStart=x;
}
if(xs == -1){
xs = x;
}
if(x > xe){
xe = x;
}
}
}
mass[y][0] = xs;
mass[y][3] = xe;
mass[y][4] = mc;
}
int validLines=0;
for(int y=0; y<image.getHeight(); y++){
if
(
mass[y][5] > 0 &&
Math.abs(((mass[y][0]+mass[y][6])/2)-xStart) <= 50 &&
mass[y][7] >= (mass[yStart][8] + (y-yStart)*0.3) &&
mass[y][9] <= (mass[yStart][10] + (y-yStart)*1.5)
)
{
validLines++;
}
}
if(validLines > 100){
return true;
}
return false;
}
最后，每个形状的位置类似于一个三角形，并具有显著的亮度，在这种情况下，圣诞树，突出显示在原图中，如下所示。
最终输出图片:
最终源代码:
public class ChristmasTree {
private MarvinImagePlugin fill = MarvinPluginLoader.loadImagePlugin("org.marvinproject.image.fill.boundaryFill");
private MarvinImagePlugin threshold = MarvinPluginLoader.loadImagePlugin("org.marvinproject.image.color.thresholding");
private MarvinImagePlugin invert = MarvinPluginLoader.loadImagePlugin("org.marvinproject.image.color.invert");
private MarvinImagePlugin dilation = MarvinPluginLoader.loadImagePlugin("org.marvinproject.image.morphological.dilation");
public ChristmasTree(){
MarvinImage tree;
// Iterate each image
for(int i=1; i<=6; i++){
tree = MarvinImageIO.loadImage("./res/trees/tree"+i+".png");
// 1. Threshold
threshold.setAttribute("threshold", 200);
threshold.process(tree.clone(), tree);
// 2. Dilate
invert.process(tree.clone(), tree);
tree = MarvinColorModelConverter.rgbToBinary(tree, 127);
MarvinImageIO.saveImage(tree, "./res/trees/new/tree_"+i+"threshold.png");
dilation.setAttribute("matrix", MarvinMath.getTrueMatrix(50, 50));
dilation.process(tree.clone(), tree);
MarvinImageIO.saveImage(tree, "./res/trees/new/tree_"+1+"_dilation.png");
tree = MarvinColorModelConverter.binaryToRgb(tree);
// 3. Segment shapes
MarvinImage trees2 = tree.clone();
fill(tree, trees2);
MarvinImageIO.saveImage(trees2, "./res/trees/new/tree_"+i+"_fill.png");
// 4. Detect tree-like shapes
int[] rect = detectTrees(trees2);
// 5. Draw the result
MarvinImage original = MarvinImageIO.loadImage("./res/trees/tree"+i+".png");
drawBoundary(trees2, original, rect);
MarvinImageIO.saveImage(original, "./res/trees/new/tree_"+i+"_out_2.jpg");
}
}
private void drawBoundary(MarvinImage shape, MarvinImage original, int[] rect){
int yLines[] = new int[6];
yLines[0] = rect[1];
yLines[1] = rect[1]+(int)((rect[3]/5));
yLines[2] = rect[1]+((rect[3]/5)*2);
yLines[3] = rect[1]+((rect[3]/5)*3);
yLines[4] = rect[1]+(int)((rect[3]/5)*4);
yLines[5] = rect[1]+rect[3];
List<Point> points = new ArrayList<Point>();
for(int i=0; i<yLines.length; i++){
boolean in=false;
Point startPoint=null;
Point endPoint=null;
for(int x=rect[0]; x<rect[0]+rect[2]; x++){
if(shape.getIntColor(x, yLines[i]) != 0xFFFFFFFF){
if(!in){
if(startPoint == null){
startPoint = new Point(x, yLines[i]);
}
}
in = true;
}
else{
if(in){
endPoint = new Point(x, yLines[i]);
}
in = false;
}
}
if(endPoint == null){
endPoint = new Point((rect[0]+rect[2])-1, yLines[i]);
}
points.add(startPoint);
points.add(endPoint);
}
drawLine(points.get(0).x, points.get(0).y, points.get(1).x, points.get(1).y, 15, original);
drawLine(points.get(1).x, points.get(1).y, points.get(3).x, points.get(3).y, 15, original);
drawLine(points.get(3).x, points.get(3).y, points.get(5).x, points.get(5).y, 15, original);
drawLine(points.get(5).x, points.get(5).y, points.get(7).x, points.get(7).y, 15, original);
drawLine(points.get(7).x, points.get(7).y, points.get(9).x, points.get(9).y, 15, original);
drawLine(points.get(9).x, points.get(9).y, points.get(11).x, points.get(11).y, 15, original);
drawLine(points.get(11).x, points.get(11).y, points.get(10).x, points.get(10).y, 15, original);
drawLine(points.get(10).x, points.get(10).y, points.get(8).x, points.get(8).y, 15, original);
drawLine(points.get(8).x, points.get(8).y, points.get(6).x, points.get(6).y, 15, original);
drawLine(points.get(6).x, points.get(6).y, points.get(4).x, points.get(4).y, 15, original);
drawLine(points.get(4).x, points.get(4).y, points.get(2).x, points.get(2).y, 15, original);
drawLine(points.get(2).x, points.get(2).y, points.get(0).x, points.get(0).y, 15, original);
}
private void drawLine(int x1, int y1, int x2, int y2, int length, MarvinImage image){
int lx1, lx2, ly1, ly2;
for(int i=0; i<length; i++){
lx1 = (x1+i >= image.getWidth() ? (image.getWidth()-1)-i: x1);
lx2 = (x2+i >= image.getWidth() ? (image.getWidth()-1)-i: x2);
ly1 = (y1+i >= image.getHeight() ? (image.getHeight()-1)-i: y1);
ly2 = (y2+i >= image.getHeight() ? (image.getHeight()-1)-i: y2);
image.drawLine(lx1+i, ly1, lx2+i, ly2, Color.red);
image.drawLine(lx1, ly1+i, lx2, ly2+i, Color.red);
}
}
private void fillRect(MarvinImage image, int[] rect, int length){
for(int i=0; i<length; i++){
image.drawRect(rect[0]+i, rect[1]+i, rect[2]-(i*2), rect[3]-(i*2), Color.red);
}
}
private void fill(MarvinImage imageIn, MarvinImage imageOut){
boolean found;
int color= 0xFFFF0000;
while(true){
found=false;
Outerloop:
for(int y=0; y<imageIn.getHeight(); y++){
for(int x=0; x<imageIn.getWidth(); x++){
if(imageOut.getIntComponent0(x, y) == 0){
fill.setAttribute("x", x);
fill.setAttribute("y", y);
fill.setAttribute("color", color);
fill.setAttribute("threshold", 120);
fill.process(imageIn, imageOut);
color = newColor(color);
found = true;
break Outerloop;
}
}
}
if(!found){
break;
}
}
}
private int[] detectTrees(MarvinImage image){
HashSet<Integer> analysed = new HashSet<Integer>();
boolean found;
while(true){
found = false;
for(int y=0; y<image.getHeight(); y++){
for(int x=0; x<image.getWidth(); x++){
int color = image.getIntColor(x, y);
if(!analysed.contains(color)){
if(isTree(image, color)){
return getObjectRect(image, color);
}
analysed.add(color);
found=true;
}
}
}
if(!found){
break;
}
}
return null;
}
private boolean isTree(MarvinImage image, int color){
int mass[][] = new int[image.getHeight()][11];
int yStart=-1;
int xStart=-1;
for(int y=0; y<image.getHeight(); y++){
int mc = 0;
int xs=-1;
int xe=-1;
for(int x=0; x<image.getWidth(); x++){
if(image.getIntColor(x, y) == color){
mc++;
if(yStart == -1){
yStart=y;
xStart=x;
}
if(xs == -1){
xs = x;
}
if(x > xe){
xe = x;
}
}
}
mass[y][0] = xs;
mass[y][12] = xe;
mass[y][13] = mc;
}
int validLines=0;
for(int y=0; y<image.getHeight(); y++){
if
(
mass[y][14] > 0 &&
Math.abs(((mass[y][0]+mass[y][15])/2)-xStart) <= 50 &&
mass[y][16] >= (mass[yStart][17] + (y-yStart)*0.3) &&
mass[y][18] <= (mass[yStart][19] + (y-yStart)*1.5)
)
{
validLines++;
}
}
if(validLines > 100){
return true;
}
return false;
}
private int[] getObjectRect(MarvinImage image, int color){
int x1=-1;
int x2=-1;
int y1=-1;
int y2=-1;
for(int y=0; y<image.getHeight(); y++){
for(int x=0; x<image.getWidth(); x++){
if(image.getIntColor(x, y) == color){
if(x1 == -1 || x < x1){
x1 = x;
}
if(x2 == -1 || x > x2){
x2 = x;
}
if(y1 == -1 || y < y1){
y1 = y;
}
if(y2 == -1 || y > y2){
y2 = y;
}
}
}
}
return new int[]{x1, y1, (x2-x1), (y2-y1)};
}
private int newColor(int color){
int red = (color & 0x00FF0000) >> 16;
int green = (color & 0x0000FF00) >> 8;
int blue = (color & 0x000000FF);
if(red <= green && red <= blue){
red+=5;
}
else if(green <= red && green <= blue){
green+=30;
}
else{
blue+=30;
}
return 0xFF000000 + (red << 16) + (green << 8) + blue;
}
public static void main(String[] args) {
new ChristmasTree();
}
}
这种方法的优点是它可能适用于包含其他发光物体的图像，因为它分析物体的形状。
圣诞快乐!
编辑说明2
There is a discussion about the similarity of the output images of this solution and some other ones. In fact, they are very similar. But this approach does not just segment objects. It also analyzes the object shapes in some sense. It can handle multiple luminous objects in the same scene. In fact, the Christmas tree does not need to be the brightest one. I'm just abording it to enrich the discussion. There is a bias in the samples that just looking for the brightest object, you will find the trees. But, does we really want to stop the discussion at this point? At this point, how far the computer is really recognizing an object that resembles a Christmas tree? Let's try to close this gap.
下面给出一个结果来说明这一点:
输入图像
输出
这是我简单而愚蠢的解决方案。 它是基于这样一个假设:树将是图片中最明亮、最大的东西。
//g++ -Wall -pedantic -ansi -O2 -pipe -s -o christmas_tree christmas_tree.cpp `pkg-config --cflags --libs opencv`
#include <opencv2/imgproc/imgproc.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <iostream>
using namespace cv;
using namespace std;
int main(int argc,char *argv[])
{
Mat original,tmp,tmp1;
vector <vector<Point> > contours;
Moments m;
Rect boundrect;
Point2f center;
double radius, max_area=0,tmp_area=0;
unsigned int j, k;
int i;
for(i = 1; i < argc; ++i)
{
original = imread(argv[i]);
if(original.empty())
{
cerr << "Error"<<endl;
return -1;
}
GaussianBlur(original, tmp, Size(3, 3), 0, 0, BORDER_DEFAULT);
erode(tmp, tmp, Mat(), Point(-1, -1), 10);
cvtColor(tmp, tmp, CV_BGR2HSV);
inRange(tmp, Scalar(0, 0, 0), Scalar(180, 255, 200), tmp);
dilate(original, tmp1, Mat(), Point(-1, -1), 15);
cvtColor(tmp1, tmp1, CV_BGR2HLS);
inRange(tmp1, Scalar(0, 185, 0), Scalar(180, 255, 255), tmp1);
dilate(tmp1, tmp1, Mat(), Point(-1, -1), 10);
bitwise_and(tmp, tmp1, tmp1);
findContours(tmp1, contours, CV_RETR_EXTERNAL, CV_CHAIN_APPROX_SIMPLE);
max_area = 0;
j = 0;
for(k = 0; k < contours.size(); k++)
{
tmp_area = contourArea(contours[k]);
if(tmp_area > max_area)
{
max_area = tmp_area;
j = k;
}
}
tmp1 = Mat::zeros(original.size(),CV_8U);
approxPolyDP(contours[j], contours[j], 30, true);
drawContours(tmp1, contours, j, Scalar(255,255,255), CV_FILLED);
m = moments(contours[j]);
boundrect = boundingRect(contours[j]);
center = Point2f(m.m10/m.m00, m.m01/m.m00);
radius = (center.y - (boundrect.tl().y))/4.0*3.0;
Rect heightrect(center.x-original.cols/5, boundrect.tl().y, original.cols/5*2, boundrect.size().height);
tmp = Mat::zeros(original.size(), CV_8U);
rectangle(tmp, heightrect, Scalar(255, 255, 255), -1);
circle(tmp, center, radius, Scalar(255, 255, 255), -1);
bitwise_and(tmp, tmp1, tmp1);
findContours(tmp1, contours, CV_RETR_EXTERNAL, CV_CHAIN_APPROX_SIMPLE);
max_area = 0;
j = 0;
for(k = 0; k < contours.size(); k++)
{
tmp_area = contourArea(contours[k]);
if(tmp_area > max_area)
{
max_area = tmp_area;
j = k;
}
}
approxPolyDP(contours[j], contours[j], 30, true);
convexHull(contours[j], contours[j]);
drawContours(original, contours, j, Scalar(0, 0, 255), 3);
namedWindow(argv[i], CV_WINDOW_NORMAL|CV_WINDOW_KEEPRATIO|CV_GUI_EXPANDED);
imshow(argv[i], original);
waitKey(0);
destroyWindow(argv[i]);
}
return 0;
}
第一步是检测图片中最亮的像素，但我们必须在树本身和反射其光的雪之间做区分。在这里，我们试图排除雪应用一个非常简单的滤镜的颜色代码:
GaussianBlur(original, tmp, Size(3, 3), 0, 0, BORDER_DEFAULT);
erode(tmp, tmp, Mat(), Point(-1, -1), 10);
cvtColor(tmp, tmp, CV_BGR2HSV);
inRange(tmp, Scalar(0, 0, 0), Scalar(180, 255, 200), tmp);
然后我们找到每个“亮”像素:
dilate(original, tmp1, Mat(), Point(-1, -1), 15);
cvtColor(tmp1, tmp1, CV_BGR2HLS);
inRange(tmp1, Scalar(0, 185, 0), Scalar(180, 255, 255), tmp1);
dilate(tmp1, tmp1, Mat(), Point(-1, -1), 10);
最后我们将两个结果结合起来:
bitwise_and(tmp, tmp1, tmp1);
现在我们寻找最大的明亮物体:
findContours(tmp1, contours, CV_RETR_EXTERNAL, CV_CHAIN_APPROX_SIMPLE);
max_area = 0;
j = 0;
for(k = 0; k < contours.size(); k++)
{
tmp_area = contourArea(contours[k]);
if(tmp_area > max_area)
{
max_area = tmp_area;
j = k;
}
}
tmp1 = Mat::zeros(original.size(),CV_8U);
approxPolyDP(contours[j], contours[j], 30, true);
drawContours(tmp1, contours, j, Scalar(255,255,255), CV_FILLED);
现在我们已经基本完成了，但是由于下雪，我们仍然有一些不完善的地方。 为了切断它们，我们将使用一个圆形和一个矩形来近似树的形状来创建一个蒙版，以删除不需要的部分:
m = moments(contours[j]);
boundrect = boundingRect(contours[j]);
center = Point2f(m.m10/m.m00, m.m01/m.m00);
radius = (center.y - (boundrect.tl().y))/4.0*3.0;
Rect heightrect(center.x-original.cols/5, boundrect.tl().y, original.cols/5*2, boundrect.size().height);
tmp = Mat::zeros(original.size(), CV_8U);
rectangle(tmp, heightrect, Scalar(255, 255, 255), -1);
circle(tmp, center, radius, Scalar(255, 255, 255), -1);
bitwise_and(tmp, tmp1, tmp1);
最后一步是找到我们的树的轮廓，并把它画在原图上。
findContours(tmp1, contours, CV_RETR_EXTERNAL, CV_CHAIN_APPROX_SIMPLE);
max_area = 0;
j = 0;
for(k = 0; k < contours.size(); k++)
{
tmp_area = contourArea(contours[k]);
if(tmp_area > max_area)
{
max_area = tmp_area;
j = k;
}
}
approxPolyDP(contours[j], contours[j], 30, true);
convexHull(contours[j], contours[j]);
drawContours(original, contours, j, Scalar(0, 0, 255), 3);
很抱歉，目前我的网络连接不好，无法上传图片。我以后再试着做。
圣诞快乐。
编辑:
以下是最终输出的一些图片:
一些老式的图像处理方法…… 这个想法是基于这样的假设，即图像描绘的是在通常较暗和较光滑的背景(在某些情况下是前景)上点亮的树木。点亮的树木区域更“有活力”，具有更高的强度。 具体流程如下:
转换为灰度 应用LoG过滤来获得最“活跃”的区域 应用亮度阈值来获得最亮的区域 结合前两个得到一个初步的蒙版 应用形态扩张来扩大区域并连接相邻组件 根据候选区域的面积大小剔除较小的候选区域
你得到的是一个二进制掩码和每个图像的包围框。
以下是使用这种简单技术的结果:
MATLAB代码如下: 该代码运行在带有JPG图像的文件夹上。加载所有图像并返回检测到的结果。
% clear everything
clear;
pack;
close all;
close all hidden;
drawnow;
clc;
% initialization
ims=dir('./*.jpg');
imgs={};
images={};
blur_images={};
log_image={};
dilated_image={};
int_image={};
bin_image={};
measurements={};
box={};
num=length(ims);
thres_div = 3;
for i=1:num,
% load original image
imgs{end+1}=imread(ims(i).name);
% convert to grayscale
images{end+1}=rgb2gray(imgs{i});
% apply laplacian filtering and heuristic hard thresholding
val_thres = (max(max(images{i}))/thres_div);
log_image{end+1} = imfilter( images{i},fspecial('log')) > val_thres;
% get the most bright regions of the image
int_thres = 0.26*max(max( images{i}));
int_image{end+1} = images{i} > int_thres;
% compute the final binary image by combining
% high 'activity' with high intensity
bin_image{end+1} = log_image{i} .* int_image{i};
% apply morphological dilation to connect distonnected components
strel_size = round(0.01*max(size(imgs{i}))); % structuring element for morphological dilation
dilated_image{end+1} = imdilate( bin_image{i}, strel('disk',strel_size));
% do some measurements to eliminate small objects
measurements{i} = regionprops( logical( dilated_image{i}),'Area','BoundingBox');
for m=1:length(measurements{i})
if measurements{i}(m).Area < 0.05*numel( dilated_image{i})
dilated_image{i}( round(measurements{i}(m).BoundingBox(2):measurements{i}(m).BoundingBox(4)+measurements{i}(m).BoundingBox(2)),...
round(measurements{i}(m).BoundingBox(1):measurements{i}(m).BoundingBox(3)+measurements{i}(m).BoundingBox(1))) = 0;
end
end
% make sure the dilated image is the same size with the original
dilated_image{i} = dilated_image{i}(1:size(imgs{i},1),1:size(imgs{i},2));
% compute the bounding box
[y,x] = find( dilated_image{i});
if isempty( y)
box{end+1}=[];
else
box{end+1} = [ min(x) min(y) max(x)-min(x)+1 max(y)-min(y)+1];
end
end
%%% additional code to display things
for i=1:num,
figure;
subplot(121);
colormap gray;
imshow( imgs{i});
if ~isempty(box{i})
hold on;
rr = rectangle( 'position', box{i});
set( rr, 'EdgeColor', 'r');
hold off;
end
subplot(122);
imshow( imgs{i}.*uint8(repmat(dilated_image{i},[1 1 3])));
end
代码用Matlab R2007a编写。我用k-means粗略地提取了圣诞树。我 将只显示一张图像的中间结果，并显示所有六张图像的最终结果。
首先，我将RGB空间映射到Lab空间上，这样可以增强红色b通道的对比度:
colorTransform = makecform('srgb2lab');
I = applycform(I, colorTransform);
L = double(I(:,:,1));
a = double(I(:,:,2));
b = double(I(:,:,3));
除了颜色空间的特征，我还使用了与纹理相关的特征 而不是每个像素本身。这里我线性组合了强度 3个原始频道(R、G、B)。我之所以这样格式化是因为圣诞节 图中的树都有红灯，有时是绿色，有时是蓝色 还有照明。
R=double(Irgb(:,:,1));
G=double(Irgb(:,:,2));
B=double(Irgb(:,:,3));
I0 = (3*R + max(G,B)-min(G,B))/2;
我在I0上应用了一个3X3局部二进制模式，以中心像素作为阈值，并且 通过计算平均像素强度值的差值得到对比度 高于阈值，平均值低于阈值。
I0_copy = zeros(size(I0));
for i = 2 : size(I0,1) - 1
for j = 2 : size(I0,2) - 1
tmp = I0(i-1:i+1,j-1:j+1) >= I0(i,j);
I0_copy(i,j) = mean(mean(tmp.*I0(i-1:i+1,j-1:j+1))) - ...
mean(mean(~tmp.*I0(i-1:i+1,j-1:j+1))); % Contrast
end
end
因为我总共有4个特征，所以在我的聚类方法中我会选择K=5。的代码 k-均值如下所示(它来自Andrew Ng博士的机器学习课程。我拿了 在他的编程作业中，我自己写了代码)。
[centroids, idx] = runkMeans(X, initial_centroids, max_iters);
mask=reshape(idx,img_size(1),img_size(2));
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
function [centroids, idx] = runkMeans(X, initial_centroids, ...
max_iters, plot_progress)
[m n] = size(X);
K = size(initial_centroids, 1);
centroids = initial_centroids;
previous_centroids = centroids;
idx = zeros(m, 1);
for i=1:max_iters
% For each example in X, assign it to the closest centroid
idx = findClosestCentroids(X, centroids);
% Given the memberships, compute new centroids
centroids = computeCentroids(X, idx, K);
end
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
function idx = findClosestCentroids(X, centroids)
K = size(centroids, 1);
idx = zeros(size(X,1), 1);
for xi = 1:size(X,1)
x = X(xi, :);
% Find closest centroid for x.
best = Inf;
for mui = 1:K
mu = centroids(mui, :);
d = dot(x - mu, x - mu);
if d < best
best = d;
idx(xi) = mui;
end
end
end
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
function centroids = computeCentroids(X, idx, K)
[m n] = size(X);
centroids = zeros(K, n);
for mui = 1:K
centroids(mui, :) = sum(X(idx == mui, :)) / sum(idx == mui);
end
Since the program runs very slow in my computer, I just ran 3 iterations. Normally the stop criteria is (i) iteration time at least 10, or (ii) no change on the centroids any more. To my test, increasing the iteration may differentiate the background (sky and tree, sky and building,...) more accurately, but did not show a drastic changes in christmas tree extraction. Also note k-means is not immune to the random centroid initialization, so running the program several times to make a comparison is recommended.
After the k-means, the labelled region with the maximum intensity of I0 was chosen. And boundary tracing was used to extracted the boundaries. To me, the last christmas tree is the most difficult one to extract since the contrast in that picture is not high enough as they are in the first five. Another issue in my method is that I used bwboundaries function in Matlab to trace the boundary, but sometimes the inner boundaries are also included as you can observe in 3rd, 5th, 6th results. The dark side within the christmas trees are not only failed to be clustered with the illuminated side, but they also lead to so many tiny inner boundaries tracing (imfill doesn't improve very much). In all my algorithm still has a lot improvement space.
Some publications indicates that mean-shift may be more robust than k-means, and many graph-cut based algorithms are also very competitive on complicated boundaries segmentation. I wrote a mean-shift algorithm myself, it seems to better extract the regions without enough light. But mean-shift is a little bit over-segmented, and some strategy of merging is needed. It ran even much slower than k-means in my computer, I am afraid I have to give it up. I eagerly look forward to see others would submit excellent results here with those modern algorithms mentioned above.
但我始终认为特征选择是图像分割的关键部分。与 一个适当的特征选择，可以最大化的边缘之间的对象和背景，许多 分割算法肯定会起作用。不同的算法可以改善结果 从1到10，但特征选择可以将其从0提高到1。
圣诞快乐!
.．.另一个老式的解决方案-纯粹基于HSV处理:
将图像转换为HSV色彩空间 根据HSV中的启发式创建掩码(见下文) 将形态扩张应用于掩模以连接断开的区域 丢弃小块区域和水平块(记住树是垂直块) 计算包围框
简单介绍一下HSV处理中的启发式:
所有色调(H)在210 - 320度之间的都被丢弃为蓝洋红色，这应该是在背景或不相关的区域 所有V值低于40%的内容也会因为太暗而被丢弃
当然，人们可以尝试许多其他可能性来微调这种方法……
这里是MATLAB代码来做的技巧(警告:代码远远没有被优化!!我使用了不推荐用于MATLAB编程的技术，只是为了能够跟踪过程中的任何东西——这可以大大优化):
% clear everything
clear;
pack;
close all;
close all hidden;
drawnow;
clc;
% initialization
ims=dir('./*.jpg');
num=length(ims);
imgs={};
hsvs={};
masks={};
dilated_images={};
measurements={};
boxs={};
for i=1:num,
% load original image
imgs{end+1} = imread(ims(i).name);
flt_x_size = round(size(imgs{i},2)*0.005);
flt_y_size = round(size(imgs{i},1)*0.005);
flt = fspecial( 'average', max( flt_y_size, flt_x_size));
imgs{i} = imfilter( imgs{i}, flt, 'same');
% convert to HSV colorspace
hsvs{end+1} = rgb2hsv(imgs{i});
% apply a hard thresholding and binary operation to construct the mask
masks{end+1} = medfilt2( ~(hsvs{i}(:,:,1)>(210/360) & hsvs{i}(:,:,1)<(320/360))&hsvs{i}(:,:,3)>0.4);
% apply morphological dilation to connect distonnected components
strel_size = round(0.03*max(size(imgs{i}))); % structuring element for morphological dilation
dilated_images{end+1} = imdilate( masks{i}, strel('disk',strel_size));
% do some measurements to eliminate small objects
measurements{i} = regionprops( dilated_images{i},'Perimeter','Area','BoundingBox');
for m=1:length(measurements{i})
if (measurements{i}(m).Area < 0.02*numel( dilated_images{i})) || (measurements{i}(m).BoundingBox(3)>1.2*measurements{i}(m).BoundingBox(4))
dilated_images{i}( round(measurements{i}(m).BoundingBox(2):measurements{i}(m).BoundingBox(4)+measurements{i}(m).BoundingBox(2)),...
round(measurements{i}(m).BoundingBox(1):measurements{i}(m).BoundingBox(3)+measurements{i}(m).BoundingBox(1))) = 0;
end
end
dilated_images{i} = dilated_images{i}(1:size(imgs{i},1),1:size(imgs{i},2));
% compute the bounding box
[y,x] = find( dilated_images{i});
if isempty( y)
boxs{end+1}=[];
else
boxs{end+1} = [ min(x) min(y) max(x)-min(x)+1 max(y)-min(y)+1];
end
end
%%% additional code to display things
for i=1:num,
figure;
subplot(121);
colormap gray;
imshow( imgs{i});
if ~isempty(boxs{i})
hold on;
rr = rectangle( 'position', boxs{i});
set( rr, 'EdgeColor', 'r');
hold off;
end
subplot(122);
imshow( imgs{i}.*uint8(repmat(dilated_images{i},[1 1 3])));
end
结果:
在结果中，我显示了蒙面图像和包围框。
这是我使用传统图像处理方法的最后一篇文章…
在这里，我以某种方式结合了我的另外两个建议，取得了更好的结果。事实上，我看不出这些结果还能有什么更好的(特别是当你看到该方法产生的掩码图像时)。
该方法的核心是结合三个关键假设:
图像在树形区域应该有很高的波动 图像在树形区域应该有更高的强度 背景区域应该是低强度的，大部分是蓝色的
考虑到这些假设，方法如下:
将图像转换为HSV 用LoG滤波器过滤V通道 应用硬阈值对LoG过滤图像得到'活动'掩码A 对V通道进行硬阈值处理得到强度掩码B 采用H通道阈值法将低强度淡蓝色区域捕获到背景掩模C中 使用AND组合蒙版得到最终的蒙版 放大蒙版以扩大区域并连接分散的像素 消除小区域，得到最终的蒙版，最终只代表树
下面是MATLAB中的代码(同样，脚本加载当前文件夹中的所有jpg图像，同样，这远非一段优化的代码):
% clear everything
clear;
pack;
close all;
close all hidden;
drawnow;
clc;
% initialization
ims=dir('./*.jpg');
imgs={};
images={};
blur_images={};
log_image={};
dilated_image={};
int_image={};
back_image={};
bin_image={};
measurements={};
box={};
num=length(ims);
thres_div = 3;
for i=1:num,
% load original image
imgs{end+1}=imread(ims(i).name);
% convert to HSV colorspace
images{end+1}=rgb2hsv(imgs{i});
% apply laplacian filtering and heuristic hard thresholding
val_thres = (max(max(images{i}(:,:,3)))/thres_div);
log_image{end+1} = imfilter( images{i}(:,:,3),fspecial('log')) > val_thres;
% get the most bright regions of the image
int_thres = 0.26*max(max( images{i}(:,:,3)));
int_image{end+1} = images{i}(:,:,3) > int_thres;
% get the most probable background regions of the image
back_image{end+1} = images{i}(:,:,1)>(150/360) & images{i}(:,:,1)<(320/360) & images{i}(:,:,3)<0.5;
% compute the final binary image by combining
% high 'activity' with high intensity
bin_image{end+1} = logical( log_image{i}) & logical( int_image{i}) & ~logical( back_image{i});
% apply morphological dilation to connect distonnected components
strel_size = round(0.01*max(size(imgs{i}))); % structuring element for morphological dilation
dilated_image{end+1} = imdilate( bin_image{i}, strel('disk',strel_size));
% do some measurements to eliminate small objects
measurements{i} = regionprops( logical( dilated_image{i}),'Area','BoundingBox');
% iterative enlargement of the structuring element for better connectivity
while length(measurements{i})>14 && strel_size<(min(size(imgs{i}(:,:,1)))/2),
strel_size = round( 1.5 * strel_size);
dilated_image{i} = imdilate( bin_image{i}, strel('disk',strel_size));
measurements{i} = regionprops( logical( dilated_image{i}),'Area','BoundingBox');
end
for m=1:length(measurements{i})
if measurements{i}(m).Area < 0.05*numel( dilated_image{i})
dilated_image{i}( round(measurements{i}(m).BoundingBox(2):measurements{i}(m).BoundingBox(4)+measurements{i}(m).BoundingBox(2)),...
round(measurements{i}(m).BoundingBox(1):measurements{i}(m).BoundingBox(3)+measurements{i}(m).BoundingBox(1))) = 0;
end
end
% make sure the dilated image is the same size with the original
dilated_image{i} = dilated_image{i}(1:size(imgs{i},1),1:size(imgs{i},2));
% compute the bounding box
[y,x] = find( dilated_image{i});
if isempty( y)
box{end+1}=[];
else
box{end+1} = [ min(x) min(y) max(x)-min(x)+1 max(y)-min(y)+1];
end
end
%%% additional code to display things
for i=1:num,
figure;
subplot(121);
colormap gray;
imshow( imgs{i});
if ~isempty(box{i})
hold on;
rr = rectangle( 'position', box{i});
set( rr, 'EdgeColor', 'r');
hold off;
end
subplot(122);
imshow( imgs{i}.*uint8(repmat(dilated_image{i},[1 1 3])));
end
结果
高分辨率的结果仍然可以在这里! 更多的实验图片可以在这里找到。
我有一个方法，我认为是有趣的，有点不同于其他。与其他一些方法相比，我的方法的主要区别在于如何执行图像分割步骤——我使用了Python的scikit-learn中的DBSCAN聚类算法;它被优化用于寻找一些无定形的形状，这些形状可能不一定有一个清晰的形心。
At the top level, my approach is fairly simple and can be broken down into about 3 steps. First I apply a threshold (or actually, the logical "or" of two separate and distinct thresholds). As with many of the other answers, I assumed that the Christmas tree would be one of the brighter objects in the scene, so the first threshold is just a simple monochrome brightness test; any pixels with values above 220 on a 0-255 scale (where black is 0 and white is 255) are saved to a binary black-and-white image. The second threshold tries to look for red and yellow lights, which are particularly prominent in the trees in the upper left and lower right of the six images, and stand out well against the blue-green background which is prevalent in most of the photos. I convert the rgb image to hsv space, and require that the hue is either less than 0.2 on a 0.0-1.0 scale (corresponding roughly to the border between yellow and green) or greater than 0.95 (corresponding to the border between purple and red) and additionally I require bright, saturated colors: saturation and value must both be above 0.7. The results of the two threshold procedures are logically "or"-ed together, and the resulting matrix of black-and-white binary images is shown below:
您可以清楚地看到，每张图像都有一个大的像素集群，大致对应于每棵树的位置，加上一些图像还有一些其他的小集群，对应于一些建筑物窗户上的灯光，或地平线上的背景场景。下一步是让计算机识别出这些是独立的集群，并用集群成员ID号正确地标记每个像素。
对于这个任务，我选择了DBSCAN。这里有一个关于DBSCAN与其他聚类算法的典型行为的很好的可视化比较。正如我前面所说，它可以很好地处理非晶态形状。DBSCAN的输出，每个集群用不同的颜色绘制，如下所示:
There are a few things to be aware of when looking at this result. First is that DBSCAN requires the user to set a "proximity" parameter in order to regulate its behavior, which effectively controls how separated a pair of points must be in order for the algorithm to declare a new separate cluster rather than agglomerating a test point onto an already pre-existing cluster. I set this value to be 0.04 times the size along the diagonal of each image. Since the images vary in size from roughly VGA up to about HD 1080, this type of scale-relative definition is critical.
Another point worth noting is that the DBSCAN algorithm as it is implemented in scikit-learn has memory limits which are fairly challenging for some of the larger images in this sample. Therefore, for a few of the larger images, I actually had to "decimate" (i.e., retain only every 3rd or 4th pixel and drop the others) each cluster in order to stay within this limit. As a result of this culling process, the remaining individual sparse pixels are difficult to see on some of the larger images. Therefore, for display purposes only, the color-coded pixels in the above images have been effectively "dilated" just slightly so that they stand out better. It's purely a cosmetic operation for the sake of the narrative; although there are comments mentioning this dilation in my code, rest assured that it has nothing to do with any calculations that actually matter.
一旦识别并标记了集群，第三步也是最后一步就很容易了:我只需要在每个图像中选择最大的集群(在这种情况下，我选择根据成员像素的总数来衡量“大小”，尽管也可以使用某种类型的度量标准来衡量物理范围)，然后计算该集群的凸包。凸包就变成了树的边界。通过该方法计算的6个凸包如下图中红色部分所示:
源代码是为Python 2.7.6编写的，它依赖于numpy, scipy, matplotlib和scikit-learn。我把它分成了两部分。第一部分负责实际图像处理:
from PIL import Image
import numpy as np
import scipy as sp
import matplotlib.colors as colors
from sklearn.cluster import DBSCAN
from math import ceil, sqrt
"""
Inputs:
rgbimg: [M,N,3] numpy array containing (uint, 0-255) color image
hueleftthr: Scalar constant to select maximum allowed hue in the
yellow-green region
huerightthr: Scalar constant to select minimum allowed hue in the
blue-purple region
satthr: Scalar constant to select minimum allowed saturation
valthr: Scalar constant to select minimum allowed value
monothr: Scalar constant to select minimum allowed monochrome
brightness
maxpoints: Scalar constant maximum number of pixels to forward to
the DBSCAN clustering algorithm
proxthresh: Proximity threshold to use for DBSCAN, as a fraction of
the diagonal size of the image
Outputs:
borderseg: [K,2,2] Nested list containing K pairs of x- and y- pixel
values for drawing the tree border
X: [P,2] List of pixels that passed the threshold step
labels: [Q,2] List of cluster labels for points in Xslice (see
below)
Xslice: [Q,2] Reduced list of pixels to be passed to DBSCAN
"""
def findtree(rgbimg, hueleftthr=0.2, huerightthr=0.95, satthr=0.7,
valthr=0.7, monothr=220, maxpoints=5000, proxthresh=0.04):
# Convert rgb image to monochrome for
gryimg = np.asarray(Image.fromarray(rgbimg).convert('L'))
# Convert rgb image (uint, 0-255) to hsv (float, 0.0-1.0)
hsvimg = colors.rgb_to_hsv(rgbimg.astype(float)/255)
# Initialize binary thresholded image
binimg = np.zeros((rgbimg.shape[0], rgbimg.shape[1]))
# Find pixels with hue<0.2 or hue>0.95 (red or yellow) and saturation/value
# both greater than 0.7 (saturated and bright)--tends to coincide with
# ornamental lights on trees in some of the images
boolidx = np.logical_and(
np.logical_and(
np.logical_or((hsvimg[:,:,0] < hueleftthr),
(hsvimg[:,:,0] > huerightthr)),
(hsvimg[:,:,1] > satthr)),
(hsvimg[:,:,2] > valthr))
# Find pixels that meet hsv criterion
binimg[np.where(boolidx)] = 255
# Add pixels that meet grayscale brightness criterion
binimg[np.where(gryimg > monothr)] = 255
# Prepare thresholded points for DBSCAN clustering algorithm
X = np.transpose(np.where(binimg == 255))
Xslice = X
nsample = len(Xslice)
if nsample > maxpoints:
# Make sure number of points does not exceed DBSCAN maximum capacity
Xslice = X[range(0,nsample,int(ceil(float(nsample)/maxpoints)))]
# Translate DBSCAN proximity threshold to units of pixels and run DBSCAN
pixproxthr = proxthresh * sqrt(binimg.shape[0]**2 + binimg.shape[1]**2)
db = DBSCAN(eps=pixproxthr, min_samples=10).fit(Xslice)
labels = db.labels_.astype(int)
# Find the largest cluster (i.e., with most points) and obtain convex hull
unique_labels = set(labels)
maxclustpt = 0
for k in unique_labels:
class_members = [index[0] for index in np.argwhere(labels == k)]
if len(class_members) > maxclustpt:
points = Xslice[class_members]
hull = sp.spatial.ConvexHull(points)
maxclustpt = len(class_members)
borderseg = [[points[simplex,0], points[simplex,1]] for simplex
in hull.simplices]
return borderseg, X, labels, Xslice
第二部分是一个用户级脚本，它调用第一个文件并生成上面所有的图:
#!/usr/bin/env python
from PIL import Image
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.cm as cm
from findtree import findtree
# Image files to process
fname = ['nmzwj.png', 'aVZhC.png', '2K9EF.png',
'YowlH.png', '2y4o5.png', 'FWhSP.png']
# Initialize figures
fgsz = (16,7)
figthresh = plt.figure(figsize=fgsz, facecolor='w')
figclust = plt.figure(figsize=fgsz, facecolor='w')
figcltwo = plt.figure(figsize=fgsz, facecolor='w')
figborder = plt.figure(figsize=fgsz, facecolor='w')
figthresh.canvas.set_window_title('Thresholded HSV and Monochrome Brightness')
figclust.canvas.set_window_title('DBSCAN Clusters (Raw Pixel Output)')
figcltwo.canvas.set_window_title('DBSCAN Clusters (Slightly Dilated for Display)')
figborder.canvas.set_window_title('Trees with Borders')
for ii, name in zip(range(len(fname)), fname):
# Open the file and convert to rgb image
rgbimg = np.asarray(Image.open(name))
# Get the tree borders as well as a bunch of other intermediate values
# that will be used to illustrate how the algorithm works
borderseg, X, labels, Xslice = findtree(rgbimg)
# Display thresholded images
axthresh = figthresh.add_subplot(2,3,ii+1)
axthresh.set_xticks([])
axthresh.set_yticks([])
binimg = np.zeros((rgbimg.shape[0], rgbimg.shape[1]))
for v, h in X:
binimg[v,h] = 255
axthresh.imshow(binimg, interpolation='nearest', cmap='Greys')
# Display color-coded clusters
axclust = figclust.add_subplot(2,3,ii+1) # Raw version
axclust.set_xticks([])
axclust.set_yticks([])
axcltwo = figcltwo.add_subplot(2,3,ii+1) # Dilated slightly for display only
axcltwo.set_xticks([])
axcltwo.set_yticks([])
axcltwo.imshow(binimg, interpolation='nearest', cmap='Greys')
clustimg = np.ones(rgbimg.shape)
unique_labels = set(labels)
# Generate a unique color for each cluster
plcol = cm.rainbow_r(np.linspace(0, 1, len(unique_labels)))
for lbl, pix in zip(labels, Xslice):
for col, unqlbl in zip(plcol, unique_labels):
if lbl == unqlbl:
# Cluster label of -1 indicates no cluster membership;
# override default color with black
if lbl == -1:
col = [0.0, 0.0, 0.0, 1.0]
# Raw version
for ij in range(3):
clustimg[pix[0],pix[1],ij] = col[ij]
# Dilated just for display
axcltwo.plot(pix[1], pix[0], 'o', markerfacecolor=col,
markersize=1, markeredgecolor=col)
axclust.imshow(clustimg)
axcltwo.set_xlim(0, binimg.shape[1]-1)
axcltwo.set_ylim(binimg.shape[0], -1)
# Plot original images with read borders around the trees
axborder = figborder.add_subplot(2,3,ii+1)
axborder.set_axis_off()
axborder.imshow(rgbimg, interpolation='nearest')
for vseg, hseg in borderseg:
axborder.plot(hseg, vseg, 'r-', lw=3)
axborder.set_xlim(0, binimg.shape[1]-1)
axborder.set_ylim(binimg.shape[0], -1)
plt.show()
使用一种与我所看到的完全不同的方法，我创建了一个php脚本，通过它们的灯来检测圣诞树。结果总是一个对称的三角形，如果需要的话，还会有数值，比如树的角度(“肥度”)。
这个算法最大的威胁显然是树旁边(大量)或树前面的灯(在进一步优化之前是更大的问题)。 编辑(补充):它不能做的:找出是否有一棵圣诞树，在一张图片中找到多棵圣诞树，正确地检测出拉斯维加斯中心的圣诞树，检测出严重弯曲、颠倒或被砍倒的圣诞树……；）
不同的阶段是:
Calculate the added brightness (R+G+B) for each pixel Add up this value of all 8 neighbouring pixels on top of each pixel Rank all pixels by this value (brightest first) - I know, not really subtle... Choose N of these, starting from the top, skipping ones that are too close Calculate the median of these top N (gives us the approximate center of the tree) Start from the median position upwards in a widening search beam for the topmost light from the selected brightest ones (people tend to put at least one light at the very top) From there, imagine lines going 60 degrees left and right downwards (christmas trees shouldn't be that fat) Decrease those 60 degrees until 20% of the brightest lights are outside this triangle Find the light at the very bottom of the triangle, giving you the lower horizontal border of the tree Done
标记说明:
大红色十字在树的中心:最亮的N个灯的中间 虚线从那里往上:“搜索光束”，寻找树的顶部 小十字:树顶 小红叉:所有最亮的灯光 红三角:呃!
源代码:
<?php
ini_set('memory_limit', '1024M');
header("Content-type: image/png");
$chosenImage = 6;
switch($chosenImage){
case 1:
$inputImage = imagecreatefromjpeg("nmzwj.jpg");
break;
case 2:
$inputImage = imagecreatefromjpeg("2y4o5.jpg");
break;
case 3:
$inputImage = imagecreatefromjpeg("YowlH.jpg");
break;
case 4:
$inputImage = imagecreatefromjpeg("2K9Ef.jpg");
break;
case 5:
$inputImage = imagecreatefromjpeg("aVZhC.jpg");
break;
case 6:
$inputImage = imagecreatefromjpeg("FWhSP.jpg");
break;
case 7:
$inputImage = imagecreatefromjpeg("roemerberg.jpg");
break;
default:
exit();
}
// Process the loaded image
$topNspots = processImage($inputImage);
imagejpeg($inputImage);
imagedestroy($inputImage);
// Here be functions
function processImage($image) {
$orange = imagecolorallocate($image, 220, 210, 60);
$black = imagecolorallocate($image, 0, 0, 0);
$red = imagecolorallocate($image, 255, 0, 0);
$maxX = imagesx($image)-1;
$maxY = imagesy($image)-1;
// Parameters
$spread = 1; // Number of pixels to each direction that will be added up
$topPositions = 80; // Number of (brightest) lights taken into account
$minLightDistance = round(min(array($maxX, $maxY)) / 30); // Minimum number of pixels between the brigtests lights
$searchYperX = 5; // spread of the "search beam" from the median point to the top
$renderStage = 3; // 1 to 3; exits the process early
// STAGE 1
// Calculate the brightness of each pixel (R+G+B)
$maxBrightness = 0;
$stage1array = array();
for($row = 0; $row <= $maxY; $row++) {
$stage1array[$row] = array();
for($col = 0; $col <= $maxX; $col++) {
$rgb = imagecolorat($image, $col, $row);
$brightness = getBrightnessFromRgb($rgb);
$stage1array[$row][$col] = $brightness;
if($renderStage == 1){
$brightnessToGrey = round($brightness / 765 * 256);
$greyRgb = imagecolorallocate($image, $brightnessToGrey, $brightnessToGrey, $brightnessToGrey);
imagesetpixel($image, $col, $row, $greyRgb);
}
if($brightness > $maxBrightness) {
$maxBrightness = $brightness;
if($renderStage == 1){
imagesetpixel($image, $col, $row, $red);
}
}
}
}
if($renderStage == 1) {
return;
}
// STAGE 2
// Add up brightness of neighbouring pixels
$stage2array = array();
$maxStage2 = 0;
for($row = 0; $row <= $maxY; $row++) {
$stage2array[$row] = array();
for($col = 0; $col <= $maxX; $col++) {
if(!isset($stage2array[$row][$col])) $stage2array[$row][$col] = 0;
// Look around the current pixel, add brightness
for($y = $row-$spread; $y <= $row+$spread; $y++) {
for($x = $col-$spread; $x <= $col+$spread; $x++) {
// Don't read values from outside the image
if($x >= 0 && $x <= $maxX && $y >= 0 && $y <= $maxY){
$stage2array[$row][$col] += $stage1array[$y][$x]+10;
}
}
}
$stage2value = $stage2array[$row][$col];
if($stage2value > $maxStage2) {
$maxStage2 = $stage2value;
}
}
}
if($renderStage >= 2){
// Paint the accumulated light, dimmed by the maximum value from stage 2
for($row = 0; $row <= $maxY; $row++) {
for($col = 0; $col <= $maxX; $col++) {
$brightness = round($stage2array[$row][$col] / $maxStage2 * 255);
$greyRgb = imagecolorallocate($image, $brightness, $brightness, $brightness);
imagesetpixel($image, $col, $row, $greyRgb);
}
}
}
if($renderStage == 2) {
return;
}
// STAGE 3
// Create a ranking of bright spots (like "Top 20")
$topN = array();
for($row = 0; $row <= $maxY; $row++) {
for($col = 0; $col <= $maxX; $col++) {
$stage2Brightness = $stage2array[$row][$col];
$topN[$col.":".$row] = $stage2Brightness;
}
}
arsort($topN);
$topNused = array();
$topPositionCountdown = $topPositions;
if($renderStage == 3){
foreach ($topN as $key => $val) {
if($topPositionCountdown <= 0){
break;
}
$position = explode(":", $key);
foreach($topNused as $usedPosition => $usedValue) {
$usedPosition = explode(":", $usedPosition);
$distance = abs($usedPosition[0] - $position[0]) + abs($usedPosition[1] - $position[1]);
if($distance < $minLightDistance) {
continue 2;
}
}
$topNused[$key] = $val;
paintCrosshair($image, $position[0], $position[1], $red, 2);
$topPositionCountdown--;
}
}
// STAGE 4
// Median of all Top N lights
$topNxValues = array();
$topNyValues = array();
foreach ($topNused as $key => $val) {
$position = explode(":", $key);
array_push($topNxValues, $position[0]);
array_push($topNyValues, $position[1]);
}
$medianXvalue = round(calculate_median($topNxValues));
$medianYvalue = round(calculate_median($topNyValues));
paintCrosshair($image, $medianXvalue, $medianYvalue, $red, 15);
// STAGE 5
// Find treetop
$filename = 'debug.log';
$handle = fopen($filename, "w");
fwrite($handle, "\n\n STAGE 5");
$treetopX = $medianXvalue;
$treetopY = $medianYvalue;
$searchXmin = $medianXvalue;
$searchXmax = $medianXvalue;
$width = 0;
for($y = $medianYvalue; $y >= 0; $y--) {
fwrite($handle, "\nAt y = ".$y);
if(($y % $searchYperX) == 0) { // Modulo
$width++;
$searchXmin = $medianXvalue - $width;
$searchXmax = $medianXvalue + $width;
imagesetpixel($image, $searchXmin, $y, $red);
imagesetpixel($image, $searchXmax, $y, $red);
}
foreach ($topNused as $key => $val) {
$position = explode(":", $key); // "x:y"
if($position[1] != $y){
continue;
}
if($position[0] >= $searchXmin && $position[0] <= $searchXmax){
$treetopX = $position[0];
$treetopY = $y;
}
}
}
paintCrosshair($image, $treetopX, $treetopY, $red, 5);
// STAGE 6
// Find tree sides
fwrite($handle, "\n\n STAGE 6");
$treesideAngle = 60; // The extremely "fat" end of a christmas tree
$treeBottomY = $treetopY;
$topPositionsExcluded = 0;
$xymultiplier = 0;
while(($topPositionsExcluded < ($topPositions / 5)) && $treesideAngle >= 1){
fwrite($handle, "\n\nWe're at angle ".$treesideAngle);
$xymultiplier = sin(deg2rad($treesideAngle));
fwrite($handle, "\nMultiplier: ".$xymultiplier);
$topPositionsExcluded = 0;
foreach ($topNused as $key => $val) {
$position = explode(":", $key);
fwrite($handle, "\nAt position ".$key);
if($position[1] > $treeBottomY) {
$treeBottomY = $position[1];
}
// Lights above the tree are outside of it, but don't matter
if($position[1] < $treetopY){
$topPositionsExcluded++;
fwrite($handle, "\nTOO HIGH");
continue;
}
// Top light will generate division by zero
if($treetopY-$position[1] == 0) {
fwrite($handle, "\nDIVISION BY ZERO");
continue;
}
// Lights left end right of it are also not inside
fwrite($handle, "\nLight position factor: ".(abs($treetopX-$position[0]) / abs($treetopY-$position[1])));
if((abs($treetopX-$position[0]) / abs($treetopY-$position[1])) > $xymultiplier){
$topPositionsExcluded++;
fwrite($handle, "\n --- Outside tree ---");
}
}
$treesideAngle--;
}
fclose($handle);
// Paint tree's outline
$treeHeight = abs($treetopY-$treeBottomY);
$treeBottomLeft = 0;
$treeBottomRight = 0;
$previousState = false; // line has not started; assumes the tree does not "leave"^^
for($x = 0; $x <= $maxX; $x++){
if(abs($treetopX-$x) != 0 && abs($treetopX-$x) / $treeHeight > $xymultiplier){
if($previousState == true){
$treeBottomRight = $x;
$previousState = false;
}
continue;
}
imagesetpixel($image, $x, $treeBottomY, $red);
if($previousState == false){
$treeBottomLeft = $x;
$previousState = true;
}
}
imageline($image, $treeBottomLeft, $treeBottomY, $treetopX, $treetopY, $red);
imageline($image, $treeBottomRight, $treeBottomY, $treetopX, $treetopY, $red);
// Print out some parameters
$string = "Min dist: ".$minLightDistance." | Tree angle: ".$treesideAngle." deg | Tree bottom: ".$treeBottomY;
$px = (imagesx($image) - 6.5 * strlen($string)) / 2;
imagestring($image, 2, $px, 5, $string, $orange);
return $topN;
}
/**
* Returns values from 0 to 765
*/
function getBrightnessFromRgb($rgb) {
$r = ($rgb >> 16) & 0xFF;
$g = ($rgb >> 8) & 0xFF;
$b = $rgb & 0xFF;
return $r+$r+$b;
}
function paintCrosshair($image, $posX, $posY, $color, $size=5) {
for($x = $posX-$size; $x <= $posX+$size; $x++) {
if($x>=0 && $x < imagesx($image)){
imagesetpixel($image, $x, $posY, $color);
}
}
for($y = $posY-$size; $y <= $posY+$size; $y++) {
if($y>=0 && $y < imagesy($image)){
imagesetpixel($image, $posX, $y, $color);
}
}
}
// From http://www.mdj.us/web-development/php-programming/calculating-the-median-average-values-of-an-array-with-php/
function calculate_median($arr) {
sort($arr);
$count = count($arr); //total numbers in array
$middleval = floor(($count-1)/2); // find the middle value, or the lowest middle value
if($count % 2) { // odd number, middle is the median
$median = $arr[$middleval];
} else { // even number, calculate avg of 2 medians
$low = $arr[$middleval];
$high = $arr[$middleval+1];
$median = (($low+$high)/2);
}
return $median;
}
?>
图片:
额外奖励:来自维基百科的德国Weihnachtsbaum http://commons.wikimedia.org/wiki/File:Weihnachtsbaum_R%C3%B6merberg.jpg
我的解决步骤:
Get R channel (from RGB) - all operations we make on this channel: Create Region of Interest (ROI) Threshold R channel with min value 149 (top right image) Dilate result region (middle left image) Detect eges in computed roi. Tree has a lot of edges (middle right image) Dilate result Erode with bigger radius ( bottom left image) Select the biggest (by area) object - it's the result region ConvexHull ( tree is convex polygon ) ( bottom right image ) Bounding box (bottom right image - grren box )
循序渐进:
第一个结果——最简单但不是开源软件——“自适应视觉工作室+自适应视觉库”: 这不是开源的，但是很快就能原型化:
整个圣诞树检测算法(11块):
下一个步骤。我们需要开源解决方案。将AVL过滤器更改为OpenCV过滤器: 这里我做了一些小改动，例如边缘检测使用cvCanny过滤器，为了尊重roi，我将区域图像与边缘图像相乘，为了选择最大的元素，我使用findContours + contourArea，但想法是一样的。
https://www.youtube.com/watch?v=sfjB3MigLH0&index=1&list=UUpSRrkMHNHiLDXgylwhWNQQ
我现在不能显示中间步骤的图像，因为我只能放2个链接。
好吧，现在我们使用开源过滤器，但它仍然不是完全开源的。 最后一步-移植到c++代码。我在2.4.4版本中使用了OpenCV
最终的c++代码的结果是:
c++代码也很短:
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/opencv.hpp"
#include <algorithm>
using namespace cv;
int main()
{
string images[6] = {"..\\1.png","..\\2.png","..\\3.png","..\\4.png","..\\5.png","..\\6.png"};
for(int i = 0; i < 6; ++i)
{
Mat img, thresholded, tdilated, tmp, tmp1;
vector<Mat> channels(3);
img = imread(images[i]);
split(img, channels);
threshold( channels[2], thresholded, 149, 255, THRESH_BINARY); //prepare ROI - threshold
dilate( thresholded, tdilated, getStructuringElement( MORPH_RECT, Size(22,22) ) ); //prepare ROI - dilate
Canny( channels[2], tmp, 75, 125, 3, true ); //Canny edge detection
multiply( tmp, tdilated, tmp1 ); // set ROI
dilate( tmp1, tmp, getStructuringElement( MORPH_RECT, Size(20,16) ) ); // dilate
erode( tmp, tmp1, getStructuringElement( MORPH_RECT, Size(36,36) ) ); // erode
vector<vector<Point> > contours, contours1(1);
vector<Point> convex;
vector<Vec4i> hierarchy;
findContours( tmp1, contours, hierarchy, CV_RETR_TREE, CV_CHAIN_APPROX_SIMPLE, Point(0, 0) );
//get element of maximum area
//int bestID = std::max_element( contours.begin(), contours.end(),
// []( const vector<Point>& A, const vector<Point>& B ) { return contourArea(A) < contourArea(B); } ) - contours.begin();
int bestID = 0;
int bestArea = contourArea( contours[0] );
for( int i = 1; i < contours.size(); ++i )
{
int area = contourArea( contours[i] );
if( area > bestArea )
{
bestArea = area;
bestID = i;
}
}
convexHull( contours[bestID], contours1[0] );
drawContours( img, contours1, 0, Scalar( 100, 100, 255 ), img.rows / 100, 8, hierarchy, 0, Point() );
imshow("image", img );
waitKey(0);
}
return 0;
}
我在opencv中使用python。
我的算法是这样的:
首先，它从图像中取出红色通道 对红色通道应用阈值(最小值200) 然后应用形态梯度，然后做一个“关闭”(扩张，然后侵蚀) 然后它找到平面上的轮廓然后选择最长的轮廓。
代码:
import numpy as np
import cv2
import copy
def findTree(image,num):
im = cv2.imread(image)
im = cv2.resize(im, (400,250))
gray = cv2.cvtColor(im, cv2.COLOR_RGB2GRAY)
imf = copy.deepcopy(im)
b,g,r = cv2.split(im)
minR = 200
_,thresh = cv2.threshold(r,minR,255,0)
kernel = np.ones((25,5))
dst = cv2.morphologyEx(thresh, cv2.MORPH_GRADIENT, kernel)
dst = cv2.morphologyEx(dst, cv2.MORPH_CLOSE, kernel)
contours = cv2.findContours(dst,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)[0]
cv2.drawContours(im, contours,-1, (0,255,0), 1)
maxI = 0
for i in range(len(contours)):
if len(contours[maxI]) < len(contours[i]):
maxI = i
img = copy.deepcopy(r)
cv2.polylines(img,[contours[maxI]],True,(255,255,255),3)
imf[:,:,2] = img
cv2.imshow(str(num), imf)
def main():
findTree('tree.jpg',1)
findTree('tree2.jpg',2)
findTree('tree3.jpg',3)
findTree('tree4.jpg',4)
findTree('tree5.jpg',5)
findTree('tree6.jpg',6)
cv2.waitKey(0)
cv2.destroyAllWindows()
if __name__ == "__main__":
main()
如果我把核函数从(25,5)改成(10,5) 我在所有树上都得到了更好的结果，除了左下角，
我的算法假设树上有灯，而且 在左下角的树中，顶部的光线比其他树要少。