albeh95's profile - activity

I've just noticed I have a lot of values like these: uncompressed_sv_total: 246 uncompressed_support_vectors:

I used one_class because i just need to classificate one object class (the goal is to classified pictures as tree pictur

I used one_class because i just need to classificate one object class

Sure, it starts like this: opencv_ml_svm: format: 3 svmType: ONE_CLASS kernel: type: LINEAR nu: 5.00000

Sure, it starts like this: opencv_ml_svm: format: 3 svmType: ONE_CLASS kernel: type: LINEAR nu: 5.0000

Loading a .yml file in a SVM Hi everyone, I trained an SVM and saved the result in a .yml file thanks to svm->save(fi

Thanks! Had just found it :)

How to check if an image is total black Hi everyone, I'm trying to check if a threshold is empty (and so, if the result

How to check if an image is total black Hi everyone, I'm trying to check if a threshold is empty (and so, if the result

I managed to get only the trees in the treshold, however I only get non-trees labels on every test pic... don't get why

Another strategy I'm trying is to delete the grass part in the image treshold (maybe by selecting only "dense" white par

Another strategy I'm trying is to delete tre grass part in the image treshold (maybe by selecting only "dense" white par

Isolate object to better detect it Hello everyone, it's me again: i'm trying to detect dome trees in a pictures and I tr

well after 3 weeks that i'm stuck on this project i chose to ask for help. is it wrong?

Detection after classification Hi everyone, I have implemented a bag of word strategy to classify images containig trees

I'm thinking about the fact that, to make the dictionary, I've used 2 images among the 63 of the training set that actua

I posted the full code, can't find the mismatch! I swear berak I'll put your name in my thesys credits when I'll graduat

Training SVM Error - Assertion failed Hello everyone, basically I have this code: #include <opencv2/imgcodecs.hpp>

Trining is 400x31 while labels is 1x32 mmm

Thank you again! So basically I only wrote Mat labels() without parameters and set the push_back() cast into int (sorry

Thank you again! So basically I only wrote Mat labels() without paameters and set the push_back() cast into int (sorry I

Thank you again! So basically I only wrote Mat labels() without paameters and set the push_back() cast into int (sorry I

Thank you again! So basically I only wrote Mat labels() without paameters and set the push_back() cast into int (sorry I

It has finished one half hour later I posted the question here, luckly it's a process that I'm suppose to do only one ti

Training SVM Error - Assertion failed Hello everyone, basically I have this code: Mat labels(0, 1, CV_32S); int dictSiz

Thank you berak, I've edited my code following your suggestion but still I get the same error. Should I do something on

Training SVM Error - Assertion failed Hello everyone, basically I have this code: cout << "extracting histograms

Cluster(Mat) function taking too long Hello everyone, I'm trying to make a dictionary using BOWKMeansTrainer class: i

Alright so basically I deleted the line int label[1] = {1}, and just defined Mat labels(0, 1, CV_32S); but still I get t

Alright so basically I deleted the line int label[1] = {1}, and just defined Mat labels(0, 1, CV_32S); but still I get t

Alright so basically I deleted the line int label[1] = {1}, and just defined Mat labels(0, 1, CV_32S); but still I get t

Bad argument on classification problem Hello guys, I'm trying to compile this code having ONLY 1 LABEL fro object classi

Bad argument on classification problem Hello guys, I'm trying to compile this code having ONLY 1 LABEL fro object classi

Mmm i don't get it, I've already used int label[1] = {1}; which in actually an int

Bad argument on classification problem Hello guys, I'm trying to compile this code having ONLY 1 LABEL fro object classi

Bad argument on classification problem Hello guys, I'm trying to compile this code having ONLY 1 LABEL fro object classi

I know, actually I don't need a perfect result: I'm not even allowed to use ml tecniques, but just opencv methods. If it

Tree detection c++ Goodmorning everyone, I'm tryin to write a c++ code for detecting trees in a image (i have a dataset

Hello berak, my dataset is actually made of 9 pics: all the trees are from a whole image including other natural element

Tree detection c++ Goodmorning everyone, I'm tryin to write a c++ code for detecting trees in a image (i have a dataset

How to estimate translation and rotation of objects using the optical flow of the related points Hello everyone, I'm wri

How to estimate translation and rotation of objects using the optical flow of the related points Hello everyone, I'm wri

thanks! now it's working!

Hi all, I've got this error in the function: "calcOpticalFlowPyrLK". Basically I have to track a book from a video given, do I used SIFT features to detect the book in the video and surrounding it with a square obtaining the following result: Then I have to track (and show) the features of the book using the pyramid Lukas-Kanade tracker, and I'm using the following code:

           for (;;) {
            //tracking

            vector<uchar> status;
            vector<float> err;
            vector<KeyPoint> next_keypoints;
            Mat result;
            if (prev_gray.empty())
            {
                gray.copyTo(prev_gray);
            }
            cap >> frame;
            cvtColor(frame, gray, COLOR_BGR2GRAY);
            calcOpticalFlowPyrLK(prev_gray, gray, keypoints_2, next_keypoints, status, err);
            drawKeypoints(prev_gray, keypoints_2, result);
            imshow("res", result);
            gray.copyTo(prev_gray);
            keypoints_2 = next_keypoints;

        }

Where "prev_gray" is an empty Mat defined at the beginning of the code (before of the SIFT obj detection), "gray" is the first frame of the video converted in gray scale and keypoints_2 is the vector<keypoint> of the first frame of the video.

At the execution of the method "calcOpticalFlowPyrLK(prev_gray, gray, keypoints_2, next_keypoints, status, err);", I'm getting the error "type: udeclared identifier (at traits.hpp)" and "type is not a member of 'cv::DataType<t>'"

What could be the problem? Thank y'all!

EDIT: Following break suggestion, I changed my code into:

                    vector<KeyPoint> next_keypoints1;
        vector<uchar> status;
        vector<float> err;
        vector<Point2f> next_keypoints;
        vector<Point2f> keypoints_frame_temp;
        vector<KeyPoint> keyponts_frame;
        for (;;) {
            //tracking

            KeyPoint::convert(keypoints_2, keypoints_frame_temp);
            Mat result;
            if (prev_gray.empty())
            {
                gray.copyTo(prev_gray);
            }
            cap >> frame;
            cvtColor(frame, gray, COLOR_BGR2GRAY);
            calcOpticalFlowPyrLK(prev_gray, gray, keypoints_frame_temp, next_keypoints, status, err);
            KeyPoint::convert(keypoints_frame_temp, keyponts_frame);
            drawKeypoints(prev_gray, keyponts_frame, result);
            imshow("res", result);
            gray.copyTo(prev_gray);
            KeyPoint::convert(next_keypoints, next_keypoints1);
            keyponts_frame = next_keypoints1;

        }

Using the KeyPoint::convert function to have the right type inside the calcOpticalFlowPyrLK(), but what I get in the "res" windows is just a blank space and I have no access to it (I can see the window, but I can't do anything on it). Is it a problem of my pc? Is it maybe not powerful enough for this?

Thank you berak you're always the best here! I followed your suggestion and I used the KeyPoint::convert function to hav

Thank you break you're always the best here! I followed your suggestion and I used the KeyPoint::convert function to hav

'type' undeclared identifier opencv traits.hpp Hi all, I've got this error in the function: "calcOpticalFlowPyrLK". Basi

'type' undeclared identifier opencv traits.hpp Hi all, I've got this error in the function: "calcOpticalFlowPyrLK". Basi