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;
}

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()

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!

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

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。