[RELEASED] OpenCV for Unity

I think the following example will be helpful for matching the frames from a live feed of a webcam.
MarkerLessARExample
https://assetstore.unity.com/packages/templates/tutorials/markerless-ar-example-77560

 

Hello,
I bought the package and so far have been very impressed! I am wondering if the plugin is able to play well with Jobs or on another worker thread? It is process heavy. I am trying to the markerless AR and track several markers and found that the Orb matching and descriptor brings the app to a halt. Any advice would be appreciated.

Thanks!

 

The following example is a good reference for Mat operations on multi-threads.
https://github.com/EnoxSoftware/Ope...nchronousFaceDetectionWebCamTextureExample.cs

 

public void OnChangeCameraButtonClick ()
{
webCamTextureToMatHelper.requestedIsFrontFacing = !webCamTextureToMatHelper.IsFrontFacing ();
}
I connected two usb cameras on the computer and use this button to switch cameras. In my opinion, this is possible, but it does not work. How can I modify it?

 

hi there !
I have some error with the playmaker's actions...all reference seems broken :/

The type or namespace name 'WebCamTextureToMatHelper' could not be found (are you missing a using directive or an assembly reference?)

it was working great with older version !
wonderfull asset , thx

 

Could you tell me the environment you tested?
OpenCVForUnity version :
OpenCVForUnityPlayMakerActions :
Unity Version :
Editor Platform :

 

thx for quick reply !

API new year BTW !

so :
OVC vers : Version 2.4.2 - December 18, 2020
OCVPM :Version 1.1.2 - December 28, 2020
Unity 2020.2.1f1
windows 10
In fact none of PM actions are working (999+)

thx !
nicolas

 

When you import OpenCVForUnity, does it include asmdef?
If it is not included, Could you remove OpenCVForUnity from the PackageManager and re-download it?

 

Hello sample works,
but i would like implement dnn Example with another caffemodel and onnx with the two exmaple libfacedetection...

when i try another caffemodel and proto... i have this message
dnn::forward_14() : OpenCV(4.5.0-dev) C:\Users\satoo\Desktop\opencv\modules\dnn\src\layers\fully_connected_layer.cpp:180: error: (-215:Assertion failed) srcMat.dims == 2 && srcMat.cols == weights.cols && dstMat.rows == srcMat.rows && dstMat.cols == weights.rows && srcMat.type() == weights.type() && weights.type() == dstMat.type() && srcMat.type() == CV_32F && (biasMat.empty() || (biasMat.type() == srcMat.type() && biasMat.isContinuous() && (int)biasMat.total() == dstMat.cols)) in function 'cv::dnn::FullyConnectedLayerImpl::FullyConnected::run'

files are in dd folder in streaming asset,...

and chen i try another onnx on th github of onnx,
unity crash!

I think I must do something wrong or put files that are probably not suitable?

i would like put this files
https://github.com/onnx/models/tree/master/vision/body_analysis/age_gender

how i cant do that with your asset?
thanks

 

Hi, macfry.

Not all inference models can be loaded by the OpenCV Dnn module. If layers included in the model do not correspond, an error or crash will occur.

Fortunately, the age_gender model you wanted could be inferred with code like this:

Code (CSharp):

1. using OpenCVForUnity.CoreModule;
2. using OpenCVForUnity.DnnModule;
3. using OpenCVForUnity.ImgcodecsModule;
4. using OpenCVForUnity.UnityUtils;
5. using System.Collections.Generic;
6. using UnityEngine;
7. using Rect = OpenCVForUnity.CoreModule.Rect;
8.  
9. /// <summary>
10. /// AgeGenderTest
11. ///
12. /// Referring to https://github.com/onnx/models/blob/master/vision/body_analysis/age_gender/levi_googlenet.py.
13. ///
14. /// Download the following files and move to the "StreamingAssets/dnn/age_gender" folder.
15. /// https://github.com/onnx/models/raw/master/vision/body_analysis/age_gender/dependencies/kid.jpg
16. /// https://github.com/onnx/models/raw/master/vision/body_analysis/age_gender/models/age_googlenet.onnx
17. /// https://github.com/onnx/models/raw/master/vision/body_analysis/age_gender/models/gender_googlenet.onnx
18. /// </summary>
19. public class AgeGenderTest : MonoBehaviour
20. {
21.  
22.     List<string> genderList = new List<string> { "Male", "Female" };
23.     List<string> ageList = new List<string> { "(0-2)", "(4-6)", "(8-12)", "(15-20)", "(25-32)", "(38-43)", "(48-53)", "(60-100)" };
24.  
25.     // Use this for initialization
26.     void Start()
27.     {
28.  
29.         //if true, The error log of the Native side OpenCV will be displayed on the Unity Editor Console.
30.         Utils.setDebugMode(true);
31.  
32.  
33.         string image_filepath = Utils.getFilePath("dnn/age_gender/" + "kid.jpg");
34.         string age_model_filepath = Utils.getFilePath("dnn/age_gender/" + "age_googlenet.onnx");
35.         string gender_model_filepath = Utils.getFilePath("dnn/age_gender/" + "gender_googlenet.onnx");
36.  
37.         Mat orig_img = Imgcodecs.imread(image_filepath);
38.         Mat img = new Mat(orig_img, new Rect(472, 102, 211, 270)); // crop image. (face region)
39.  
40.         Net age_net = Dnn.readNetFromONNX(age_model_filepath);
41.         Net gender_net = Dnn.readNetFromONNX(gender_model_filepath);
42.  
43.        
44.         Mat input = Dnn.blobFromImage(img, 1.0, new Size(224, 224), new Scalar(104, 117, 123), true, false, CvType.CV_32F);
45.  
46.  
47.         // gender classification
48.         gender_net.setInput(input);
49.         Mat genders = gender_net.forward();
50.         Core.MinMaxLocResult gender_max = Core.minMaxLoc(genders);
51.         int gender_idx = (int)gender_max.maxLoc.x;
52.  
53.         Debug.Log("Gender: " + genderList[gender_idx]);
54.  
55.  
56.         // age classification
57.         age_net.setInput(input);
58.         Mat ages = age_net.forward();
59.         Core.MinMaxLocResult age_max = Core.minMaxLoc(ages);
60.         int age_idx = (int)age_max.maxLoc.x;
61.  
62.         Debug.Log("Age: " + ageList[age_idx]);
63.  
64.  
65.         Utils.setDebugMode(false);
66.     }
67. }

 

I will try!!! thanks a lot!

 

it's work fine on a picture but i would like try this with webcamtexture...

 

CV vtuber example, it's working fine except the video capture example; I can't get it to work. In fact, any of the video capture examples (OpenCV or DlibFaceLandmarkDetector video capture examples).


ArgumentException: imgMat.isContinuous() must be true.
CVVTuber.OpenCVForUnityUtils.SetImage (DlibFaceLandmarkDetector.FaceLandmarkDetector faceLandmarkDetector, OpenCVForUnity.CoreModule.Mat imgMat) (at Assets/CVVTuberExample/CVVTuber/Scripts/Utils/OpenCVForUnityUtils.cs:32)
CVVTuber.DlibFaceLandmarkGetter.UpdateValue () (at Assets/CVVTuberExample/CVVTuber/Scripts/DlibFaceLandmarkGetter.cs:216)
CVVTuber.CVVTuberControllManager.Update () (at Assets/CVVTuberExample/CVVTuber/Scripts/Core/CVVTuberControllManager.cs:52)

 

Could you tell me the environment you tested?
OpenCVForUnity version :
DlibFaceLandmarkDetector version :
CVVTuberExample version :
Unity Version :
Editor Platform :

 

OpenCVForUnity: 2.4.2
DlibFaceLandmarkDetector version :1.3.2
CVVTuberExample version :1.0.6
Unity Version : 2019.4.18f1
Editor Platform : windows 7 sp1.

 

The system requirement for OpenCVForUnity is Windows 8 or later. Does the error occur in Windows 8 or later?

 

I seem to have "found" a bug in the plugin:
Defining and initializing a MatOfDouble inside a class works if the Unity Editor is already running but if I exit Unity it crashes on startup.

The line causing the crash is (dummy code):

Code (CSharp):

1. public class abc : MonoBehaviour
2. {
3.      private MatOfDouble mat = new MatOfDouble(new double[] { 0, 0, 0, 0 });
4. }

This code works without issues if I add it in the script while Unity is running but if I exit the Editor and then start it again, with no changes in the previously working script, it crashes on startup.

If I initialize the variable in e.g. the Awake function I can close Unity and open it again without issues (dummy code):

Code (CSharp):

1. public class abc : MonoBehaviour
2. {
3.      private MatOfDouble mat;
4.  
5.      void Awake() {
6.           mat = new MatOfDouble(new double[] { 0, 0, 0, 0 });
7.      }
8. }

Looking into the Editor.log created by Unity during the crash this is the core error message:

After a short Google search a similar issue seemed to exist in a different project: https://www.noesisengine.com/bugs/view.php?id=1538
As their workaround is basically the same that I came up with and they diagnosed an issue in their project I think this also is a bug in the plugin and not in my code or Unity itself.

I was able to reproduce the issue in Unity 2019.4.17f1 and 2019.4.18f1 with Windows 10 and plugin version 2.4.2.

 

Hi,
I am working with the Yolo Object Detection example. I am trying to figure out how to overlay a ui element or gameobject on the detected object bounding box. I've searched and can't seem to find a solution. I know this here creates the bounding box

Code (CSharp):

1. Imgproc.rectangle(frame, new Point(left, top), new Point(right, bottom), new Scalar(0, 255, 0, 255), 2);

Is there a way to grab those point and convert them into a Vector3?


I attached an image with the desired result.

 

Thank you very much for reporting.
The cause of this bug is currently under investigation.

 

I think the attached file will help you.
This example shows how to overlay a 3D object on the center of a detected face.

 

Thank you!! That worked exactly how I needed it to.

 

Hi,
Can I use GStreamer for backend of VideoCapture class on Windows?
I installed GStreamer 1.18.3. But the following code does not work well.

Code (CSharp):

1. VideoCapture capture;
2. capture.open("videotestsrc ! videoconvert ! appsink");

 

In order to use Gstreamer, you need to enable Gstreamer and recompile OpenCV.
I've custom built a gstreamer-enabled OpenCV before and combined it with OpenCVForUnity.
For more details, see the section on “How to use OpenCV Dynamic Link Library with customized build settings” in ReadMe.pdf.

I have successfully connected the rtsp protocol by following the steps below.
1. Follow the instructions on the following page to build OpenCV dynamic library.
https://funvision.blogspot.com/2020/03/compile-opencv-4-for-visual-studio-2019.html
OpenCV4.5.0
https://github.com/opencv/opencv/tree/78476a0fe25b761dfda813f9ba030e5d7f1aa82f
https://github.com/opencv/opencv_contrib/tree/37315babf9984a5b6aa981644a20dd8df1a5ff02


2. Copy “OpenCVForUnity\Extra\dll_version\Windows\” to
“OpenCVForUnity\Plugins\Windows\”.
3. Copy the built OpenCV dynamic library to the "OpenCVForUnity\Plugins\Windows\" folder.

4. Change to the attached VideoCaptureExample.cs.

capture.open("videotestsrc ! videoconvert ! appsink", Videoio.CAP_GSTREAMER);

capture.open("rtspsrc location=rtsp://91.191.213.49:554/live_mpeg4.sdp latency=0 dulation=-1 ! decodebin ! videoconvert ! appsink", Videoio.CAP_GSTREAMER);

 

Hi, i'm testing the aruco example scenes but i am having a problem. When i use the dummy camera matrix everything goes well, but when i try to calibrate it with the calibration example scene, and use the new camera matrix and distortion coefficients in the webcam aruco example scene, it draws well the corners and pose (so i guess i did a good calibration), but something is off, since it offsets the ar cube, as you can see in the following images:


I tried calibrating multiples times and i always get the same result. Does someone know what could be happening?
I'm just using the example scenes without any modification and the last OpenCVForUnity with a logitech c920 hd pro, which has very little distortion. I also noted that this horizontal error offset of the cube position is proportionally similar to the difference between the default cx component of the camera matrix and the calibrated cx component of the matrix.

 

Hi,

I'm working in a project: I have a picture, inside this picture I know N coplanar points (I have the world 3d coordinates and the coordinates in the image). I want to find out the camera position of the camera for the image. I managed to get it to work for python, but in your plugin I'm getting wrong output values for the same input data:

Python code:

Code (CSharp):

1.  
2. print(f'FIELD objectPoints {world_points}\nimagePoints {screen_points}\ncamMatrix {camera_matrix}\ndistCoeffs {dist_coeffs}');
3.             _ret, rvec, tvec = cv.solvePnP(world_points, screen_points, camera_matrix, dist_coeffs, cv.SOLVEPNP_IPPE)
4.             print(f'FIELD rvec {rvec}\ntvec {tvec}');
5.  

C# code:

Code (CSharp):

1.            
2. Debug.Log($"FIELD objectPoints {objectPoints.dump()}\nimagePoints {imagePoints.dump()}\ncamMatrix {camMatrix.dump()}\ndistCoeffs {distCoeffs.dump()}");
3.             Calib3d.solvePnP(objectPoints, imagePoints, camMatrix, distCoeffs, rvec, tvec, true, Calib3d.SOLVEPNP_IPPE);
4.             Debug.Log($"FIELD rvec {rvec.dump()}\ntvec {tvec.dump()}");
5.  

Python output:

Code (CSharp):

1.  
2. FIELD objectPoints [[ 52.5    0.    34.  ]
3. [ 52.5    0.    -3.66]
4. [ 36.     0.   -20.16]
5. [ 41.5    0.     0.  ]]
6. imagePoints [[ 471.35842368  338.10150168]
7. [1740.883776    567.4959036 ]
8. [1561.767552    866.02291884]
9. [ 936.43209408  581.065272  ]]
10. camMatrix [[6.28360766e+03 0.00000000e+00 9.60000000e+02]
11. [0.00000000e+00 6.28360766e+03 5.40000000e+02]
12. [0.00000000e+00 0.00000000e+00 1.00000000e+00]]
13. distCoeffs [[0.]
14. [0.]
15. [0.]
16. [0.]]
17. FIELD rvec [[ 0.13082996]
18. [-0.57601962]
19. [-0.02956267]]
20. tvec [[-34.96040194]
21. [  3.35909129]
22. [ 62.97022695]]
23.  

C# output:

Code (CSharp):

1.  
2. FIELD objectPoints [52.5, 0, 34;
3. 52.5, 0, -3.6600001;
4. 36, 0, -20.16;
5. 41.5, 0, 0]
6. imagePoints [471.35843, 338.1015;
7. 1740.8838, 567.49591;
8. 1561.7676, 866.02295;
9. 936.43207, 581.06531]
10. camMatrix [6283.60791015625, 0, 960;
11. 0, 6283.60791015625, 540;
12. 0, 0, 1]
13. distCoeffs [0;
14. 0;
15. 0;
16. 0]
17. FIELD rvec [0.1538111422233873;
18. -0.6324571644188874;
19. -0.02627024069205628]
20. tvec [-32.95994179269246;
21. 3.826083621349714;
22. 72.16430511224465]
23.  

Any idea why?

 

Thank you very much for the detailed instructions.

I followed the instructions and was able to display video in case of videotestsrc. However, in the case of rtspsrc, it does not work well. Only the first retrieve() works and the image is displayed, but after that retrieve() does not work at all.

I try using the same GStreamer command sequence for my C++ program using the same DLLs on the same PC, and there is no problem, the streaming video is displayed continuously.

What should I do?

 

There are three types of camera parameters that can be obtained by OpenCV calibration: internal parameters (camera matrix), distortion parameters, and external parameters.
To get a perfect fit between the AR object and the camera image, you will probably need to set distortion parameters for the Unity Camera. You will probably need to use a shader for this.

 

Thank you very much for reporting.

Is OpenCV version the same in Python and C# Code?
OpenCVForUnity uses OpenCV 4.5.0.
https://github.com/opencv/opencv/tree/78476a0fe25b761dfda813f9ba030e5d7f1aa82f
https://github.com/opencv/opencv_contrib/tree/37315babf9984a5b6aa981644a20dd8df1a5ff02

 

The previous code was wrong. Could you please change it to the following?

Code (CSharp):

1. capture.open("rtsp://wowzaec2demo.streamlock.net/vod/mp4:BigBuckBunny_115k.mov", Videoio.CAP_GSTREAMER);

Code (CSharp):

1.             capture.grab();
2.             if (capture.retrieve(rgbMat))
3.             {

 

This is the result of a similar test code running on C++.

c++ code:

Code (CSharp):

1.  
2. #include <opencv2/opencv.hpp>
3. #include <opencv2/highgui/highgui.hpp>
4. #include <opencv2/imgproc.hpp>
5. #include <opencv2/calib3d.hpp>
6.  
7. using namespace std;
8. using namespace cv;
9.  
10. int main(void)
11. {
12.     vector<Point3f> objectPoints;
13.     objectPoints.push_back(Point3d(52.5, 0, 34));
14.     objectPoints.push_back(Point3d(52.5, 0, -3.6600001));
15.     objectPoints.push_back(Point3d(36, 0, -20.16));
16.     objectPoints.push_back(Point3d(41.5, 0, 0));
17.     vector<Point2f> imagePoints;
18.     imagePoints.push_back(Point2d(471.35843, 338.1015));
19.     imagePoints.push_back(Point2d(1740.8838, 567.49591));
20.     imagePoints.push_back(Point2d(1561.7676, 866.02295));
21.     imagePoints.push_back(Point2d(936.43207, 581.06531));
22.     Mat camMatrix = (cv::Mat_<double>(3, 3) << 6283.60791015625, 0, 960,
23.         0, 6283.60791015625, 540,
24.         0, 0, 1);
25.     Mat distCoeffs = (cv::Mat_<double>(4, 1) << 0, 0, 0, 0);
26.  
27.     Mat rvec, tvec;
28.     solvePnP(objectPoints, imagePoints, camMatrix, distCoeffs, rvec, tvec, true, SOLVEPNP_IPPE);
29.  
30.     cout << "objectPoints : " << objectPoints << endl;
31.     cout << "imagePoints : " << imagePoints << endl;
32.     cout << "camMatrix : " << camMatrix << endl;
33.     cout << "distCoeffs : " << distCoeffs << endl;
34.     cout << "rvec : " << rvec << endl;
35.     cout << "tvec : " << tvec << endl;
36.  
37.     cv::waitKey(0);
38. }
39.  

c++ output:

Code (CSharp):

1. objectPoints: [52.5, 0, 34;
2.     52.5, 0, -3.6600001;
3.     36, 0, -20.16;
4.     41.5, 0, 0]
5.     imagePoints : [471.35843, 338.1015;
6.     1740.8838, 567.49591;
7.     1561.7676, 866.02295;
8.     936.43207, 581.06531]
9.         camMatrix : [6283.60791015625, 0, 960;
10.     0, 6283.60791015625, 540;
11.     0, 0, 1]
12.         distCoeffs : [0;
13.     0;
14.     0;
15.     0]
16.         rvec : [0.1538111422233873;
17.     -0.6324571644188874;
18.     -0.02627024069205628]
19.         tvec : [-32.95994179269246;
20.     3.826083621349714;
21.     72.16430511224465]

I think the difference between C++ / C# (OpenCVForUnity) and python results is a python binding issue.

 

@EnoxSoftware I have an interesting issue. I am using the face mask example with open cv and dlib.

Thee is a crash whenever this f(x) is called. Utils.texture2DToMat()

The log stack trace leads back to here. OpenCVForUnity_ByteArrayToMatData()


Unity 2018.3.6f1
Open CV version 2.4.2 (according to the readme.pdf)
Building for UWP.

Has you or anyone encountered this issue before? How can I fix this? Thanks in advance!

 

Having issues with Cloud Build on a project using this library. "opencv2 not found in dylib search path"

Platform: iOS
OCV4U Version: 2.4.2
Unity Version: 2019.4.19f1
Unity Version (Cloud Build): 2019.4.18f1 (Latest 2019.4 available in Cloud Build)

I'm able to build the project without issue for Android. Builds for Windows fine as well.

I don't generally build iOS apps locally - I have an older MacMini that I use for Keychain to set up app signing, but it's not suitable for building on any more - so I have no idea if this problem occurs on a local XCode build.


The key issue comes up here:

36112:     Search Path: /APPLICATION_PATH/Xcode12_2_0.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/lib/clang/12.0.0/lib/darwin, /APPLICATION_PATH/Xcode12_2_0.app/Contents/Developer/Toolchains/XcodeDefault.xctoolchain/usr/lib/swift/iphoneos, /APPLICATION_PATH/Xcode12_2_0.app/Contents/Developer/Platforms/iPhoneOS.platform/Developer/SDKs/iPhoneOS14.2.sdk/usr/lib, /APPLICATION_PATH/Xcode12_2_0.app/Contents/Developer/Platforms/iPhoneOS.platform/Developer/SDKs/iPhoneOS14.2.sdk/System/Library/Frameworks

36113:     opencv2 not found in dylib search path

36114: Stderr:

36115: >

36116:     /APPLICATION_PATH/Xcode12_2_0.app/Contents/Developer/usr/bin/ipatool:373:in `run'

36117:     /APPLICATION_PATH/Xcode12_2_0.app/Contents/Developer/usr/bin/ipatool:2808:in `block in CompileOrStripBitcodeInBundle'

36118:     /APPLICATION_PATH/Xcode12_2_0.app/Contents/Developer/usr/bin/ipatool:2747:in `each'

36119:     /APPLICATION_PATH/Xcode12_2_0.app/Contents/Developer/usr/bin/ipatool:2747:in `CompileOrStripBitcodeInBundle'

36120:     /APPLICATION_PATH/Xcode12_2_0.app/Contents/Developer/usr/bin/ipatool:3016:in `block in ProcessIPA'

36121:     /APPLICATION_PATH/Xcode12_2_0.app/Contents/Developer/usr/bin/ipatool:2978:in `each'

36122:     /APPLICATION_PATH/Xcode12_2_0.app/Contents/Developer/usr/bin/ipatool:2978:in `ProcessIPA'

36123:     /APPLICATION_PATH/Xcode12_2_0.app/Contents/Developer/usr/bin/ipatool:3928:in `<main>'}

36124: ** EXPORT FAILED **

 

It seems to "import settings" are not correct.
Please make sure it is set as follows.

 

Sorry for the late response.

I put

Debug.Log(capture.getBackendName()); 

after

capture.open(...); 

in your code.
Then I tried several cases:

• capture.open("videotestsrc ! videoconvert ! appsink");

  • Test pattern is displayed and the console says GSTREAMER.

• capture.open("rtsp://wowzaec2demo.streamlock.net/vod/mp4:BigBuckBunny_115k.mov");

  • An animated movie is displayed and the console says FFMPEG.

• capture.open("rtsp://wowzaec2demo.streamlock.net/vod/mp4:BigBuckBunny_115k.mov", Videoio.CAP_GSTREAMER);

  • Unity Editor hangs.

• capture.open("rtspsrc location=rtsp://wowzaec2demo.streamlock.net/vod/mp4:BigBuckBunny_115k.mov ! decodebin ! videoconvert ! appsink");

  • Unity Editor hangs.

I still can't successfully capture RTSP streaming video using GStreamer backend.

 

Currently, this stream does not seem to be working.
Even if I run gstreamer directly at the command prompt, receiving the stream fails.

Code (CSharp):

1. gst-launch-1.0 rtspsrc location=rtsp://wowzaec2demo.streamlock.net/vod/mp4:BigBuckBunny_115k.mov ! decodebin !  autovideosink

 

Hi everyone.

Apologies if this has been asked and please point me in a direction if needed but I've searched the forum and have not resolved my question.

I am new to the product but from what I have played with so far it is fantastic. I am in need of some guidance on feasibility to do an activity. I have played with the detection side for detecting circles etc, but is it possible to match against non standard geometric shapes. I don't want to go down an incorrect rabbit warren. I am after a pointer to the docs or similar if it can be done but can post code later if needed. I have uploaded two images for an indication of what kind of shapes they are.

Is it possible to pattern match these against a database and how? Also is it possible to outline so I can determine the area (with reference sizing information) so I can provide size discriminators as well as shape?

Any assistance that can be provided is welcomed. Or if you need further info I can provide.

Love the product.

Cheers.

 

Hello there again, I wanted to ask something is that are there any asset that can be used to only detect colour within a specific place and is it able to be built to the front-camera (selfie camera) on android as well? if so please let me know

 

Perhaps MatchShapesExample will be helpful.
https://github.com/EnoxSoftware/Ope...proc/MatchShapesExample/MatchShapesExample.cs

https://docs.opencv.org/4.5.0/d5/d45/tutorial_py_contours_more_functions.html
https://learnopencv.com/shape-matching-using-hu-moments-c-python/

 

For color detection, you may find the MultiObjectTrackingBasedOnColorExample useful.
https://github.com/EnoxSoftware/Ope...ple/MultiObjectTrackingBasedOnColorExample.cs

 

hello, I have trouble in building it to android for some reason

 

Hi enox software,

I have purchased both the latest versions of opencvforunty and dliblandmarkdetector packages last month. I am happy with what I got. I have a question regarding the AR Head Example that had been done under the landmark detection examples. I am trying to see how the AR head can be replaced with a Texture 2D image. I also came across a similar question posted on this thread earlier where you had asked them to download the ARHeadTexture2D example from the drop box and try. I have done that but the moment I import the library into Unity 2020, it gives errors in the editor. Can you kindly advice.

Thanks

 

Do I have to buy that separately and how ?

 

oh yes... thanks for the reply, I appreciate it. Do you know if I can use both MultiObjectTrackingBasedOnColorExample and WebCamTextureFaceTrackerExample in the same scene and same quad running? I am having a very hard time with this. let me know, please. thankyou

 

This package is compatible with newer versions.
ARHeadTexture2DExample_OpenCV2.4.3_Dlib1.3.2.unitypackage

 

can I get a reply on this one as I needed it fast? thanks in advance though

 

It is possible to combine the two examples. However, I do not have such an example.

 

i see, do i have to change the script drastically?

 

i keep on getting this error

Code (CSharp):

1. Object reference not set to an instance of an object
2. OpenCVForUnityExample.MultiObjectTrackingBasedOnColorExample.OnWebCamTextureToMatHelperInitialized

any suggestion?

 

Could you send me the code you've tested?
https://enoxsoftware.com/opencvforunity/contact/technical-inquiry/

 

Thanks for the fast reply, I really appreciate it. And yes, I've sent the code just now. Thanks for the assistance once again