For agricultural field
i use calcOpticalFlowFarneback methhod to recieve this
image from an image sequence, it seems very robust.
But I have trouble with next steps - to find cut/uncut grass field borderline.
AdaptiveThreshold, erote and dilate methods don't provides me good results and don't seems reliable on video feed - maybe i just messed up with parameters:
adaptiveThreshold(grayFrame, bw, 255, ADAPTIVE_THRESH_MEAN_C, THRESH_BINARY_INV, 11, 1);
Mat verticalStructure = getStructuringElement(MORPH_ELLIPSE, Size(1, 2));
erode(bw, bw2, verticalStructure, Point(-1,-1),3);
dilate(bw, bw2, verticalStructure, Point(-1,-1),3);
Mat structuringElement = getStructuringElement(MORPH_ELLIPSE, Size(2, 4));
morphologyEx( bw2, bw2, MORPH_CLOSE, structuringElement, Point(-1,-1), 3);
Should I try another approach such as neural networks, Kalman filters, or can I receive results from my first step - grayscale image?
"""Should i try another approach such as neural networks, Kalman filters, or can can i receive result from my first step - grayscale image?"""
answer Yes, I would try another approach. This is the type of thing that neural nets have been doing quite well on. There are several "out of the box" pretrained segmentation networks (try a U-net first) that will give you a head start.
You will need to:
-use a bunch of images to create your labeled data: create a mask over the un-harvested areas.
-"finetune" the net with your data. keras finetuning documentation
Of course, as with any such problem, you may run into other hurdles like:
-how big of images/crops to use
-how to predict a whole image
-and, most of all, assuming you can perfectly mask the un-cut areas of your field images, does your problem actually get solved? The exercise I always do is to pretend I have a black box that will give me my perfect results (in your case, a nice binary mask)...then complete the entire task downstream of that. If it solves the problem then it's worth spending time doing the machine learning...and if not, it's a waste of time.
Related
I am working on project what detect hematoma from skin. I am having issue with color after convertion from RGB to HSV. My algorithm detect hematoma by its color.
With some images I have good results like here:
Original img: http://imgur.com/WHiOWdj
Result img: http://imgur.com/PujbnHa
But with some images i have bad result like this:
Original img: http://imgur.com/OshB99r
Result img: http://imgur.com/CuNzAId
The same original image after convertion to HSV: http://imgur.com/lkVwtCs
Do you have any ideas how to fix it?
Thanks
Looking at your result image I think that you are only using the H channel of the original image in your algorithm. The false positive detection can inherit from that the some part of the healty skin has quite the same H value than the hematoma has. You can see on the qrey-scale image of H channel that both parts have similar values:
The difference between the two parts is the saturation value. On the following image you can see the S channel of the original image and it shows perfectly that at the hematoma the saturation is much higher than at other the part of the arm:
This was expected because the hematoma has much stronger color than the healty skin has.
So, I suggest you to use both H and S channel in your algorithm that is you have to take into account only that parts of H image where the S image contains high saturation values. A possible and simple solution to do that is that you binarize both H and S images and with an AND operation you can execute this filtering:
H image after binarisation:
S image after binarisation:
Image after H&S operation:
You can see that on the result image only the hematoma part is white (except some noise but you can eliminate easily, for example by size or by morphological filtering).
EDIT
Important to note that binarization is one of most important (and sometimes also very complicated) step in the object detection algorithms namely binarization is the first highlight of the objects to detect.
If the the external conditions (lighting, color of objects etc.) do not change significantly from image to image you can use fix binaraziation thresholds. If this constant environment can not be issured you have to use more complicated methods. There are a lot of possibilies you can use, here you can read some examples:
Wikipedia - Thresholding
Wikipedia - Balanced histogram thresholding
Several solutions are based on the histogram analysis: on the histograms with objects there are always more local maximums which positions can vary depend on the environment and if you find them you can adapt the binarization threshold easily.
For example the histogram of the H channel of the original image is the following:
The first maximum belongs to the background, the second to the skin and the last to the hematome. It can be supposed that these 3 thresholds can be found in each image only their positions vary depend on the lighting or on other conditions. To put a threshold between the 2nd and the 3rd local maximum it can be a good choice to highlight the hematome.
Finally I offer you the read the following articel about thresholding in OpenCV:
OpenCV - Thresholding
For my college project I need to identify a species of a plant from plant leaf shape by detecting edges of a leaf. (I use OpenCV 2.4.9 and C++), but the source image has taken in the real environment of the plant and has more than one leaf. See the below example image. So here I need to extract the edge pattern of just one leaf to process further.
Using Canny Edge Detector I can identify edges of the whole image.
But I don't know how to proceed from here to extract edge pattern of just one leaf, may be more clear and complete leaf. I don't know even if this is possible also. Can anyone please tell me if this is possible how to extract edges of one leaf I just want to know the image peocessing steps that I need to apply to the image. I don't want any code samples. I'm new to image processing and OpenCV and learning by doing experiments.
Thanks in advance.
Edit
As Luis said said I have done Morphological close to the image after doing edge detection using Canny edge detection, but it seems still it is difficult me to find the largest contour from the image.
Here are the steps I have taken to process the image
Apply Bilateral Filter to reduce noise
bilateralFilter(img_src, img_blur, 31, 31 * 2, 31 / 2);
Adjust contrast by histogram equaliztion
cvtColor(img_blur,img_equalized,CV_BGR2GRAY);
Apply Canny edge detector
Canny(img_equalized, img_edge_detected, 20, 60, 3);
Threshold binary image to remove some background data
threshold(img_edge_detected, img_threshold, 1, 255,THRESH_BINARY_INV);
Morphological close of the image
morphologyEx(img_threshold, img_closed, MORPH_CLOSE, getStructuringElement(MORPH_ELLIPSE, Size(2, 2)));
Following are the resulting images I'm getting.
This result I'm getting for the above original image
Source image and result for second image
Source :
Result :
Is there any way to detect the largest contour and extract it from the image ?
Note that my final target is to create a plant identification system using real environmental image, but here I cannot use template matching or masking kind of things because the user has to take an image and upload it so the system doesn't have any prior idea about the leaf.
Here is the full code
#include <opencv\cv.h>
#include <opencv\highgui.h>
using namespace cv;
int main()
{
Mat img_src, img_blur,img_gray,img_equalized,img_edge_detected,img_threshold,img_closed;
//Load original image
img_src = imread("E:\\IMAG0196.jpg");
//Apply Bilateral Filter to reduce noise
bilateralFilter(img_src, img_blur, 31, 31 * 2, 31 / 2);
//Adjust contrast by histogram equaliztion
cvtColor(img_blur,img_equalized,CV_BGR2GRAY);
//Apply Canny edge detector
Canny(img_equalized, img_edge_detected, 20, 60, 3);
//Threshold binary image to remove some background data
threshold(img_edge_detected, img_threshold, 15, 255,THRESH_BINARY_INV);
//Morphological close of the image
morphologyEx(img_threshold, img_closed, MORPH_CLOSE, getStructuringElement(MORPH_ELLIPSE, Size(2, 2)));
imshow("Result", img_closed);
waitKey(0);
return 0;
}
Thank you.
Well there is a similar question that was asked here:
opencv matching edge images
It seems that edge information is not a good descriptor for the image, still if you want to try it I'll do the following steps:
Load image and convert it to grayscale
Detect edges - Canny, Sobel try them and find what it suits you best
Set threshold to a given value that eliminates most background - Binarize image
Close the image - Morphological close dont close the window!
Count and identify objects in the image (Blobs, Watershed)
Check each object for a shape (assuming you have described shapes of the leaf you could find before or a standard shape like an ellipse) features like:
http://docs.opencv.org/modules/imgproc/doc/structural_analysis_and_shape_descriptors.html
http://www.math.uci.edu/icamp/summer/research_11/park/shape_descriptors_survey.pdf
If a given object has a given shape that you described as a leaf then you detected the leaf!.
I believe that given images are taken in the real world these algorithm will perform poorly but it's a start. Well hope it helps :).
-- POST EDIT 06/07
Well since you have no prior information about the leaf, I think the best we could do is the following:
Load image
Bilateral filter
Canny
Extract contours
Assume: that the contour with the largest perimeter is the leaf
Convex hull the 3 or 2 largest contours (the blue line is the convex hull done)
Use this convex hull to do a graph cut on the image and segmentate it
If you do those steps, you'll end up with images like these:
I won't post the code here, but you can check it out in my messy github. I hope you don't mind it was made in python.
Leaf - Github
Still, I have a couple of things to finish that could improve the result.. Roadmap would be:
Define the mask in the graphcut (like its described in the doc)
Apply region grow may give a better convex hull
Remove all edges that touch the border of the image can help to identify larger edges
Well, again, I hope it helps
I have come across one problem when trying to train data with SVM.
I get some different regions (set of connected pixels) from face images, and regions from eyes are very similar, so I want to use Hu moments for shape description and SVM for training.
But SVM does not work properly, method svm.predict evaluates afterwards everything as non-eye, moreover the same regions which were labeled and used in traning phase as eye, are evaluated as non-eye.
Feature data consists only of 7 Hu moments. I will post here some samples of source code in a moment, thanks in advance :)
Additional info:
input image:
http://i.stack.imgur.com/GyLO0.png
Setting up basic svm for 1 image:
int image_regions = 10;
Mat training_mat(image_regions ,7,CV_32FC1); // 7 hu moments
Mat labels(image_regions ,1,CV_32FC1); // for labels 1 (eye) and -1 (non eye)
// computing hu moments
Moments moments2=moments(croppedImage,false);
double hu[7];
HuMoments(moments2,hu);
// putting them into svm traning mat
for (int k=0;k<huCounter;k++)
training_mat.at<float>(counter,k) = hu[k]; // counter is current number of region
if (isEye(...))
{
labels.at<float>(counter,0)=1.0;
}
else
{
labels.at<float>(counter,0)=-1.0;
}
//I use the following:
CvSVM svm;
CvSVMParams params;
params.svm_type = CvSVM::C_SVC;
params.kernel_type = CvSVM::LINEAR;
params.term_crit = cvTermCriteria(CV_TERMCRIT_ITER, 1000, 1e-6);
// ... do the above mentioned phase, and then:
svm.train(training_mat, labels, Mat(), Mat(), params);
I hope the following suggestions can help you…..
The simplest task is to use a clustering algorithm and try to cluster the data into two classes. If an algorithm like ‘k-means’ can do the job why make things complex by using SVM and Neural Nets. I suggest you use this technique because your feature vector dimension is of a very small size (7 Hu Moments) as well as your number of samples.
Perform feature Normalization (specified in point 4) to make sure the values fall in a limited range.
Check out “is your data really separable?” As your data is small, take a few samples from positive images and a few samples from negative images and plot the feature vectors. If you can visually see the difference surely any learning algorithm can do the job for you. As I said earlier simple tricks can do better than complex math.
Only if you then decide to use SVM you should know the following:
• As I can see from your code you are using a Linear SVM, may be your data is non-separable by a linear kernel. Try using some polynomial kernel or other kernels. There is one option bool CvSVM::train_auto in openCV just have a look.
• Try to check whether the feature vector values you are getting are proper values or not (make sure that they are not some garbage values).
• Also you can perform feature normalization “ZERO MEAN and UNIT VARIENCE” before you use it for training.
• Most importantly increase the number of images for training, both positively and negatively labeled.
• Last but not least SVM is not magic, at the end of the day it is just drawing a line between two sets of points. So don’t expect it to classify anything you give it as input.
If nothing works “Just improve your feature extraction technique”
I've been trying to stitch low quality, low resolution (320x180) images, taken by a quadrocopter, in OpenCV recently. Here is what i got:
http://postimg.org/gallery/1rqsycyk/
The pictures taken are almost nadir and as you can see overlapping much. Between each shot is a translation and i tried to place objects on the ground that keep the scene almost planar not to disturb the requirements for a homography. Anyway quite many pictures are not taken into account during the stitching process.
Here another example, (only three images are stitched together):
http://postimg.org/gallery/1wpt3lmo/
I'm using the Surf Featuredetector and believe that the low quality of the images is not working out right for it but i'm not sure about that.
Here's the code i use, i found it on a similar question OpenCV non-rotational image stitching and decided to use it since it worked better than mine:
Mat pano;
Stitcher stitcher = Stitcher::createDefault(false);
stitcher.setWarper(new PlaneWarper());
stitcher.setFeaturesFinder(new detail::SurfFeaturesFinder(1000,3,4,3,4));
stitcher.setRegistrationResol(0.1);
stitcher.setSeamEstimationResol(0.1);
stitcher.setCompositingResol(1);
stitcher.setPanoConfidenceThresh(1);
stitcher.setWaveCorrection(true);
stitcher.setWaveCorrectKind(detail::WAVE_CORRECT_HORIZ);
stitcher.setFeaturesMatcher(new detail::BestOf2NearestMatcher(false,0.3));
stitcher.setBundleAdjuster(new detail::BundleAdjusterRay());
Stitcher::Status status = Stitcher::ERR_NEED_MORE_IMGS;
try{
status = stitcher.stitch(picturesTaken, pano);
}
catch(cv::Exception e){}
My other guess is to do the stitching process manually instead of using the Stitcher class, but i'm not sure if it would change much. So the question is: how can i make the stitching process more robust despite of the low quality of the images? Also: does defining ROIs have only an impact on the performance or also on the chance of actual stitching?
The result is not that bad given the quality of the input images!
To improve the quality of the output, I would do (in priority order):
an estimation of the camera distortion in order to fix it and make the matching easier
perform some histogram or lighting equalization before stitching
try to increase the temporal gap between pictures or use another stitcher. A part of the blur in the output is created by the stitcher when merging the images in their overlap areas.
I believe the problem is that you take pictures of textureless regions and it's hard to extract good distinctive keypoints from such smooth regions.
I found this question, which was very helpful for me. I investigate this theme and I have some other tips for you:
About finding similar images:
You set SURFFeatureFidner with minHessian = 1000. It is really big value (OpenCV suggest 300, I use sometimes 100). This is why there are only matches not all images.
You set PanoConfidendceThresh to "1", maybe you should set "0.8", it will stitch more images.
About the look of stitched images:
There are some other function in pipeline of Stitcher. Try to use:
stitcher.setSeamFinder(new detail::GraphCutSeamFinder(GraphCutSeamFinderBase::COST_COLOR))
stitcher.setBlender( detail::Blender::createDefault(Blender::MULTI_BAND, false))
stitcher.setExposureCompensator (detail::ExposureCompensator::createDefault(ExposureCompensator::GAIN_BLOCKS) )
Maybe this will be helpful for you!
Some people in this Q & A site suggested I use findContour to imitate what bwlabel in Matlab. But I am not sure because I think a contour is closed shape of detected edges and element from bwlabel is a connected shape. I guess they might be logically the same. What about them in practice? Are they really same?
Use either of these two library....cvBlobslib or cvblob...you will get many features about the connected components such as size and contour and ellipticity and bounding box...you can filter blobs and add togethar 2 or more blobs...try it..under the hood algo of bwlabel is a two scan connected component where as cvblob or cvBlobslib is a one scan algo...
bwlabel will give you the image connected components, i.e. different label for different connected objects in a background.
Probably what you mean is the combination of im2bw and imcontours provides, i.e. a combination of binarizing the image and trivially finding the single contour (boundaries) per retained object on the output.
Consider the following example:
I = imread('coins.png'); % grayscale
level = graythresh(I); % find thershold
BW = im2bw(I, level); % threshold image
imcontour(BW, 1); % plot single contour
For a grayscale image you can increase the number of requested contours, though findContours operates on binary images.
I found an exact article about this. Quick answer is "Yeah, their eventual output will be the same." So I might go with findContour after all considering cvBlob still using old C-style API and having its own implementation of finding contours.