I try to subtract using bitwise_and and BackgroundSubtractor but I have this error: > OpenCV Error: Assertion failed ((mtype == CV_8U || mtype == CV_8S) && _mask.sameSize(*psrc1)) in cv::binary_op, file C:\build\master_winpack-build-win64-vc14\opencv\modules\core\src\arithm.cpp, line 241
code:
Mat frame1;
Mat frame_mask;
bool bSuccess = cap.read(frame1);
if (!bSuccess) //if not success, break loop
{
cout << "Cannot read a frame from video stream" << endl;
break;
}
pMOG2->apply(frame1, frame_mask);
Mat kernel = Mat::ones(frame1.size(), CV_8UC1);
erode(frame1, frame_mask, kernel);
bitwise_and(frame1, frame1, frame, frame_mask);
Error occurs when I use bitwise_and(...).
I used OpenCV 3.2.0 and VS15.
I'm pretty new at the OpenCV, so could you please say, what I do wrong? Thank you.
↧
Background subtraction
↧
detect nail from image
i want detect nail size from image
how remove noise and detect nail
Use the code below:
Mat binary;
Mat image = imread("img/nail3.jpg");
if (!image.data)
return;
cvtColor(image, binary, CV_BGR2GRAY);
Mat result;
threshold(binary, result, 180, 255, THRESH_BINARY_INV);
Mat element = getStructuringElement(MORPH_RECT, cv::Size(5, 10));
morphologyEx(result, result, CV_MOP_OPEN, element);
namedWindow("result");
imshow("result", result);
result is:
thanks
↧
↧
ANN in opencv 3
Hi,
I was trying to run this example found in this forum:
#include
using namespace std;
using namespace cv;
using namespace cv::ml;
int main(int argc, char* argv[])
{
//create random training data
Mat_ data(100, 100);
randn(data, Mat::zeros(1, 1, data.type()), Mat::ones(1, 1, data.type()));
//half of the samples for each class
Mat_ responses(data.rows, 2);
for (int i = 0; i responses(data.rows, 1);
for (int i=0; i layerSizes(1, 3);
layerSizes(0, 0) = data.cols;
layerSizes(0, 1) = 100;
layerSizes(0, 2) = responses.cols;
Ptr network = ANN_MLP::create();
network->setLayerSizes(layerSizes);
network->setActivationFunction(ANN_MLP::SIGMOID_SYM, 0.1, 0.1);
network->setTrainMethod(ANN_MLP::BACKPROP, 0.1, 0.1);
Ptr trainData = TrainData::create(data, ROW_SAMPLE, responses);
network->train(trainData);
if (network->isTrained())
{
printf("Predict one-vector:\n");
Mat result;
network->predict(Mat::ones(1, data.cols, data.type()), result);
cout << result << endl;
printf("Predict training data:\n");
for (int i=0; ipredict(data.row(i), result);
cout << result << endl;
}
}
return 0;
}
Unfortunately, I'm not able to understand the meaning of the output: im my case, considering my test data, I obtain something like: [0.20409864, -0.15044725]
what does it mean? should I obtain a label class, isn't it? Am I doind something wrong?
↧
Problem with Opencv 3.2.0 to use the TLD tracker example.
I managed to implement the OpenCV 3.2.0 library on Visual Studio 2015 under Windows 7 64bits (https: //www.youtube.com/watch? V = gXzsh ...), I can see the video stream of My camera thanks to the function included in it but when I take the test program give by OpenCV to use the tracker and more particularly the TLD. (http://docs.opencv.org/trunk/d2/d0a/tutorial_introduction_to_tracker.html)
I have several errors:
-Error (active) identifier "Tracker" not defined 24
-Error (active) a name followed by '::' must be a class or namespace name 24
-Error C2065 'Tracker': identifier not declared 24
-Error C2923 'cv :: Ptr': 'Tracker' is not a valid model argument for parameter 'T' 24
-Error C2653 'TrackerKCF': is not a class name or a namespace 24
-Error C3861 'create': identifier not found 24
-Error C2514 'cv :: Ptr': class has no constructor 24
-Error (active) identifier "selectROI" not defined 30
-Error C3861 'selectROI': identifier not found 30
-Error C2678 '->' binary: no operator found accepting a left-hand operand of type 'cv :: Ptr' (or there is no acceptable conversion) 35
-C2039 'init' error: is not a member of 'cv :: Ptr' 35
-Error C2678 '->' binary: no operator found accepting a left-hand operand of type 'cv :: Ptr' (or there is no acceptable conversion) 45
-Error C2039 'update': is not a member of 'cv :: Ptr' 45
I saw that I missed the file tracker.hpp so I added it thanks to the source code on the OpenCV master by adding also other file with the same method but in the end I always have errors:
-LNK2001
-LNK1120
Did I do something wrong when adding OpenCV 3.2.0 or something ?? Thank you for your help.
↧
How is the EMDL1() function different from EMD() function in OpenCV?
What is the difference between EMDL1() and EMD() function in OpenCV? What does 'L1' signify? Please provide suggestions.
↧
↧
Meaning of Output of Artificial Neural Network
I have successfully trained ANN. I have tested it with one of the training sample as shown below and it gives me two outputs:-
Mat_ output;
float out = ann->predict(hists.row(8), output);
cout << "ANN Output = " << out << endl;
writeMatToFile(output, "ANNPredict.csv");
The value stored in the variable ***out*** is 2 and the values in the ***Mat output*** are:-
[0.499678 0.500128 0.500167 0.499947 0.499756 0.499937]
which is a row matrix. I trained and tested ANN with 6 classes. My question is, does the value returned by function ***predict()*** an index to a column with right prediction (high value) in the above matrix?
↧
Set multiple rows and single column at the same time in Matrix
Hi,
i'd like to know how to set multiple rows and single column at the same time in Matrix.
Ex:
Mat my_matrix = Mat::zeros(100, 4, CV_32S);
suppose that I want to set:
- rows 0-24 column 1 as 1;
- rows 25-49 column 2 as 1;
- rows 50-74 column 3 as 1;
- rows 75-99 column 4 as 1;
↧
How to Store a Mat data of Size (1920*1080) and Use it in another program?
Hello!! I am using Opencv with C++ and I want to Store a Mat of size (1920*1080) and use that in another program.
The options that I have:
1. I could store the Mat data as an Image and can access it in another program or I can store all the values in a file and can access it. But, the most important thing in my implementation is speed as I need to process 60 frames in a second.
2. I can take all the values in a header and could initialise to a Mat but it keeps on building the program and I haven't looked at the performance.
I am looking for a Solution to access the Mat very efficiently. Thank you in Advance!!
↧
How can I use the NormHistogramCostExtractor class? What function do I need to call to extract the cost? What are the arguments to be passed ?
What does norm based cost extraction mean? Do I have to normalize the histogram and then pass the normalized histograms for cost extraction as in EMDL1 or anything else? Please provide suggestions.
↧
↧
Understanding how cv::detail::leaveBiggestComponent() function works in opencv 3.2
I am having troubles understanding how the function [cv::detail::leaveBiggestComponent][1] works, as little to no documentation is available.
I know what the function is supposed to do, that is, given a set of keypoint matches between images, returning the largest subset of images with consistent matches. In addition, according to what its implementations states, it should also remove image duplicates.
The function is part of the [Stitching Pipeline][5] of opencv, and, if one refers to Brown and Lowe paper, should perform as panorama recognition module.
However, when it comes to breaking down the code, I can't really understand how this is done.
**TL;DR** I'm looking for a pseudocode explanation of the flowchart of cv::detail::leaveBiggestComponent(), please help.
The code implementation is [here][2]. It calls relevant code (with no documentation either) from [here][4] (implementation) and [here][3] (headers).
Of particular interest is the working principle of cv::detail::DisjointSets(), too.
[1]: http://docs.opencv.org/trunk/d7/d74/group__stitching__rotation.html#ga855d2fccbcfc3b3477b34d415be5e786 "cv::detail::leaveBiggestComponent docs"
[2]: https://github.com/opencv/opencv/blob/master/modules/stitching/src/motion_estimators.cpp#L1037 "Link to github repo"
[3]:
https://github.com/opencv/opencv/blob/master/modules/stitching/include/opencv2/stitching/detail/util.hpp "Link to github repo"
[4]:
https://github.com/opencv/opencv/blob/master/modules/stitching/src/util.cpp "Link to github repo"
[5]:
http://docs.opencv.org/2.4/modules/stitching/doc/introduction.html "opencv image stitching pipeline docs"
↧
How can I deal with cv::matchTemplate crashing for large images?
This problem only happens for UMat arguments, and only if us OpenCl is switched on as well.
I am guessing that the program is running out of GPU memory. This is apparently not supposed to be possible because the driver can do virtual memory. An alternative explanation is that TDR is the cause, but the computer doesn't freeze at any time so I don't think this is it.
Of course in the real program I will shrink the large images down before template matching, but since my program is for doing batches, I hope to call matchTemplate from a few windows threadpool threads to try and get higher throughput anyway. This also causes the crash. OpenCl gives us no way of getting the amount of free video memory, so I was thinking of making the number of parallel matchTemplate calls as a function of the total GPU memory amount.
The error comes out of clEnqueueReadbuffer, which returns -4 (CL_MEM_OBJECT_ALLOCATION_FAILURE);
Some code:
// OpenCvMyBuildTemplateMatchingTest.cpp : Defines the entry point for the console application.
//
#include "stdafx.h"
#include
#include
#include
#include
#include
#include
using namespace std::chrono;
milliseconds DoMatTemplateMatching();
milliseconds DoUMatTemplateMatching();
void ContinuousUMatTemplateMatching();
cv::String PatchUri = "patch.bmp";
cv::String PictureUri = "notpatch.bmp";
int _numberOfTimesToRun = 32;
bool _useOpenCl = true;
int main()
{
milliseconds _totalMatElapsed = milliseconds::zero();
milliseconds _totalUMatElapsed = milliseconds::zero();
cv::ocl::setUseOpenCL(_useOpenCl);
for (int i = 0; i<_numberOfTimesToRun; i++)
{
_totalUMatElapsed += DoUMatTemplateMatching();
}
std::cout << "\n";
std::cout << "\nUMAT template matching took " << _totalUMatElapsed.count() << " milliseond for " <<
_numberOfTimesToRun << " runs.\n";
std::cout << "\n";
for (int i = 0; i < _numberOfTimesToRun; i++)
{
_totalMatElapsed += DoMatTemplateMatching();
}
std::cout << "\n";
std::cout << "\nMAT template matching took " << _totalMatElapsed.count() << " milliseond for " <<
_numberOfTimesToRun <<" runs.\n";
std::cout << "\n";
cv::ocl::setUseOpenCL(false);
for (int i = 0; i<_numberOfTimesToRun; i++)
{
_totalUMatElapsed += DoUMatTemplateMatching();
}
std::cout << "\n";
std::cout << "\nUMAT without OpenCl template matching took " << _totalUMatElapsed.count() << " milliseond
for " << _numberOfTimesToRun << " runs.\n";
std::cout << "\n";
getch();
return 0;
}
milliseconds DoMatTemplateMatching()
{
cv::Mat _picture = cv::imread(PictureUri);
cv::Mat _patch = cv::imread(PatchUri);
cv::Mat _result;
milliseconds _startTime = duration_cast< milliseconds >(system_clock::now().time_since_epoch());
cv::matchTemplate(_picture, _patch, _result, 0);
milliseconds _endTime = duration_cast< milliseconds >(system_clock::now().time_since_epoch());
milliseconds _deltaTime = _endTime - _startTime;
return _deltaTime;
}
milliseconds DoUMatTemplateMatching()
{
cv::Mat _picture = cv::imread(PictureUri);
cv::Mat _patch = cv::imread(PatchUri);
milliseconds _startTime = duration_cast< milliseconds >(system_clock::now().time_since_epoch());
/// need to convert to greyscale or else get that error:
cv::cvtColor(_picture, _picture, CV_BGR2GRAY);
cv::cvtColor(_patch, _patch, CV_BGR2GRAY);
cv::UMat _uPicture = _picture.getUMat(cv::ACCESS_READ);
cv::UMat _uPatch = _patch.getUMat(cv::ACCESS_READ);
assert(_uPatch.type() == _uPicture.type());
std::cout << _uPatch.type();
cv::UMat _result;
cv::matchTemplate(_uPicture, _uPatch, _result, CV_TM_SQDIFF);
milliseconds _endTime = duration_cast< milliseconds >(system_clock::now().time_since_epoch());
milliseconds _deltaTime = _endTime - _startTime;
_picture.release();
_patch.release();
return _deltaTime;
}
void ContinuousUMatTemplateMatching()
{
while (true)
{
std::cout << "\n" << DoUMatTemplateMatching().count() << "\n";
}
}
The images I used in the above test:
https://drive.google.com/file/d/0B_LsZxeKoN9eckZpSGdCN2tuNU0/view?usp=sharing
https://drive.google.com/file/d/0B_LsZxeKoN9edlI5WUZxeVZTalk/view?usp=sharing
Some system info:
Number of platforms 1
Platform Name NVIDIA CUDA
Platform Vendor NVIDIA Corporation
Platform Version OpenCL 1.2 CUDA 8.0.0
Platform Profile FULL_PROFILE
Platform Extensions cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_fp64 cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_nv_d3d10_sharing cl_khr_d3d10_sharing cl_nv_d3d11_sharing cl_nv_copy_opts cl_nv_create_buffer
Platform Extensions function suffix NV
Platform Name NVIDIA CUDA
Number of devices 1
Device Name GeForce GT 610
Device Vendor NVIDIA Corporation
Device Vendor ID 0x10de
Device Version OpenCL 1.1 CUDA
Driver Version 382.33
Device OpenCL C Version OpenCL C 1.1
Device Type GPU
Device Available Yes
Device Profile FULL_PROFILE
Device Topology (NV) PCI-E, 01:00.0
Max compute units 1
Max clock frequency 1620MHz
Compute Capability (NV) 2.1
Max work item dimensions 3
Max work item sizes 1024x1024x64
Max work group size 1024
Compiler Available Yes
Preferred work group size multiple 32
Warp size (NV) 32
Preferred / native vector sizes
char 1 / 1
short 1 / 1
int 1 / 1
long 1 / 1
half 0 / 0 (n/a)
float 1 / 1
double 1 / 1 (cl_khr_fp64)
Half-precision Floating-point support (n/a)
Single-precision Floating-point support (core)
Denormals Yes
Infinity and NANs Yes
Round to nearest Yes
Round to zero Yes
Round to infinity Yes
IEEE754-2008 fused multiply-add Yes
Support is emulated in software No
Correctly-rounded divide and sqrt operations No
Double-precision Floating-point support (cl_khr_fp64)
Denormals Yes
Infinity and NANs Yes
Round to nearest Yes
Round to zero Yes
Round to infinity Yes
IEEE754-2008 fused multiply-add Yes
Support is emulated in software No
Correctly-rounded divide and sqrt operations No
Address bits 64, Little-Endian
Global memory size 1073741824 (1024MiB)
Error Correction support No
Max memory allocation 268435456 (256MiB)
Unified memory for Host and Device No
Integrated memory (NV) No
Minimum alignment for any data type 128 bytes
Alignment of base address 4096 bits (512 bytes)
Global Memory cache type Read/Write
Global Memory cache size 16384 (16KiB)
Global Memory cache line size 128 bytes
Image support Yes
Max number of samplers per kernel 16
Max 2D image size 16384x16384 pixels
Max 3D image size 2048x2048x2048 pixels
Max number of read image args 128
Max number of write image args 8
Local memory type Local
Local memory size 49152 (48KiB)
Registers per block (NV) 32768
Max constant buffer size 65536 (64KiB)
Max number of constant args 9
Max size of kernel argument 4352 (4.25KiB)
Queue properties
Out-of-order execution Yes
Profiling Yes
Profiling timer resolution 1000ns
Execution capabilities
Run OpenCL kernels Yes
Run native kernels No
Kernel execution timeout (NV) No
Concurrent copy and kernel execution (NV) Yes
Number of async copy engines 1
Device Extensions cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_fp64 cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll cl_nv_d3d10_sharing cl_khr_d3d10_sharing cl_nv_d3d11_sharing cl_nv_copy_opts cl_nv_create_buffer
↧
OpenCV Fails to Install on Ubuntu 16.10 using ICC and ICPC
Hi all,
I'll try to provide as much detail as possible off the bat. I'm using Ubuntu 16.10 with Intel ICC and ICPC installed and I want to compile OpenCV such that it can be run by Caffe. I am using the latest version of Cuda 8.0 with NVIDIA drivers.
About my hardware -- I have a system with 2 Xeons (`Intel(R) Xeon(R) CPU E5-2630 v4 @ 2.20GHz`), `nproc` will return 40, and 4x NVIDIA Tesla P100 (`Tesla P100-PCIE-16GB`). I have tried to specify the architecture of my cards below.
I've used the following CMake options:
```
sudo CC=/opt/intel/bin/icc CXX=/opt/intel/bin/icpc cmake \
-DCMAKE_BUILD_TYPE=Release \
-DCMAKE_INSTALL_PREFIX=/opt/opencv \
-DBUILD_PNG=OFF \
-DBUILD_TIFF=OFF \
-DBUILD_TBB=OFF \
-DBUILD_JPEG=OFF \
-DBUILD_JASPER=OFF \
-DBUILD_ZLIB=OFF \
-DBUILD_opencv_java=OFF \
-DBUILD_opencv_python2=OFF \
-DBUILD_opencv_python3=OFF \
-DWITH_OPENCL=OFF \
-DWITH_OPENMP=OFF \
-DWITH_FFMPEG=ON \
-DWITH_GSTREAMER=OFF \
-DWITH_GSTREAMER_0_10=OFF \
-DWITH_CUDA=ON \
-DWITH_GTK=ON \
-DWITH_VTK=OFF \
-DWITH_TBB=ON \
-DWITH_1394=OFF \
-DWITH_OPENEXR=OFF \
-DCUDA_TOOLKIT_ROOT_DIR=/usr/local/cuda-8.0 \
-DWITH_V4L=ON \
-DWITH_QT=OFF \
-DINSTALL_TESTS=OFF \
-DENABLE_FAST_MATH=1 \
-DCUDA_FAST_MATH=1 \
-DCUDA_NVCC_FLAGS="-D_FORCE_INLINES" \
-DENABLE_PRECOMPILED_HEADERS=OFF \
-DWITH_IPP=OFF \
-DBUILD_LIBPROTOBUF_FROM_SOURCES=ON \
-DCUDA_ARCH_NAME="Manual" \
-DCUDA_ARCH_BIN="52 60" \
-DCUDA_ARCH_PTX="60" \
-DWITH_CUBLAS=ON \
-DWITH_CUDA=ON \
-DBUILD_PERF_TESTS=OFF \
-DBUILD_TESTS=OFF \
-DWITH_GTK=OFF \
-DWITH_OPENCL=OFF \
-DBUILD_opencv_java=OFF \
-DBUILD_opencv_python2=OFF \
-DBUILD_opencv_python3=OFF \
-DBUILD_EXAMPLES=OFF \
-D WITH_OPENCL=OFF \
-D WITH_OPENCL_SVM=OFF \
-D WITH_OPENCLAMDFFT=OFF \
-D WITH_OPENCLAMDBLAS=OFF \
..
```
Additionally, I've attached the output of a verbose attempt at building OpenCV. After running the above `cmake` command I ran `sudo make VERBOSE=1 &>log.txt` to generate the output. In the logs, if you see `` it's because I removed the name of the user/file in the path.
The output of the make can be found here: https://www.dropbox.com/s/8wfvgquj08kgp5b/log.txt?dl=0
If I can provide any other information please let me know. Any and all help is greatly appreciated.
↧
In the Histogram Cost Extractor module, what does the values returned by buildcostMatrix function signify?
I am using buildcostMatrix function and passing it 2 arguments which are the descriptors of two images. I am getting a matrix of double. But it is very huge and therefore hard to comprehend. Can anyone please explain how to make sensible information out of the huge matrix which is returned by the function?
void buildCostMatrix (InputArray descriptors1, InputArray descriptors2, OutputArray costMatrix)
↧
↧
How to use cpp-tutorial-pnp_detection in real time camera
Hi,
I tried to use cpp-tutorial-pnp_detection in opencv sample code. I compile it successfully and can use in the box video, which is provided in opencv master.
However, I know cpp-tutorial-pnp_detection can be used in real time camera but I cannot find information about how to use it.
Has someone used in that way? Could you please give me some ideas?
Thanks in advance
↧
The hausdorff distance is not zero even when 2 same images are passed
I am passing 2 same images in hausdorff and shapeContextDistanceExtractor to calculate distance. We are expecting the answer to be zero since the images are same but we are getting a non-zero value. Can somebody please explain why.
// Hausdorff Distant Extractor
Ptr model = createHausdorffDistanceExtractor();
dist = model->computeDistance(c1, c2);> I am passing 2 images and extracting the points using samplecounters. Here c1 and c2 are the vector of countour points which are passed to the computeDistance function.
The 2 images that I pass are same yet the distance I am getting in dist is non-zero. Please help.
↧
Creating 360 degree spherical panoramas with Stitching Detailed
I want to create spherical panorama image with https://github.com/opencv/opencv/blob/master/samples/cpp/stitching_detailed.cpp.
I want to create image like generated by Panotools (http://www.panotools.org/dersch/).
Sample image,
https://commons.wikimedia.org/wiki/File:The_Facade_of_Birla_Auditorium,_A_360_Panorama-interactive_100_Pix_HDR-20130301.JPG
Does this example support this functionality ? If yes, how ?
↧
intellisense stops working after installing opencv via nuget
Hi,
I installed opencv using nuget package manager in visual studio 2015, but as soon as it gets installed all code suggestions and error report stops working. Intellisense does not work. If I uninstall opencv, everything starts working fine. Why this kind of behaviour? its very annoying to work without code suggestions on large projects. please suggest some workaround for this.
↧
↧
Store entries of vector as columns in eigen3 matrix
Hello guys,
I'm fairly new to OpenCV and working with C++ in general, so I'm sorry if this seems trivial.
The work I've already done is mostly the stuff covered in this tutorial:
http://docs.opencv.org/2.4/doc/tutorials/features2d/feature_homography/feature_homography.html
Now, I have a vector of Point2d, as generated in the Tutorial
//-- Localize the object
std::vector obj;
std::vector scene;
for( int i = 0; i < good_matches.size(); i++ )
{
//-- Get the keypoints from the good matches
obj.push_back( keypoints_object[ good_matches[i].queryIdx ].pt );
scene.push_back( keypoints_scene[ good_matches[i].trainIdx ].pt );
}
Now, what I want to do is store these Points in a matrix given by the eigen3 Package for Bundle Adjustment. So I have initialised two matrices
void BundleAdjustment::feedMatches(const ImagePair& epair)
{
// 2 x m eigen3 matrices storing P_i, P_j from vector format
MatrixXd eP_i = MatrixXd(2, epair.P_i.size());
MatrixXd eP_j = MatrixXd(2, epair.P_j.size());
So now, what I want to do, is take the two points I have in every entry of obj or scene and put them in the columns of the matrices eP_i and eP_j. How would I do that? Since the entries are of the type Point2d and not tupels of numbers, I cant seem to get the compiler to accept it. And I cant seem to recast it to another type either.
Any help would be appreciated!
↧
GStreamer + OpenCV using Raspberry Pi + Mac OSX
The current problem I am working on is to send stream from Raspberry Pi to Mac OSX using Gstreamer
and extract frames from Gstreamer using OpenCV. Here is my code:
Mac:
cv::VideoCapture cap("tcpclientsrc host=129.31.224.100 port=8888 ! gdpdepay ! rtph264depay ! avdec_h264 ! "
"videoconvert ! appsink");
if (!cap.isOpened()) {
printf("=ERR= can't create video capture\n");
return -1;
}
RPi:
gst-launch-1.0 wrappercamerabinsrc ! video/x-raw,
framerate=30/1, width=1280, height=720, format=RGB !
videoconvert ! vtenc_h264 ! h264parse !
rtph264pay config-interval=1 pt=96 ! gdppay !
tcpserversink host=129.31.224.100 port=8888
The error message is:
VIDEOIO(cvCreateFileCapture_AVFoundation (filename)): raised unknown C++ exception!
=ERR= can't create video capture
The thing I want to achieve is to read frames from gstreamer by using OpenCV.
The above command works in command line, but not working in C++ code.
Thank you in advance!
↧
Is there a way to "tilt" haar cascad for face detection
I'm quite a noob in Opencv . I m using the Haar cascade for face detection . however when i pivot the image it doesn't work any more .how solve this problem .I m using
c++
↧