Merge pull request #28444 from abhishek-gola:added_ORT_wrapper

Added ONNX Runtime as an optional wrapper #28444

This PR adds ONNXRuntime (ORT) as an _optional_ wrapper, which can be enabled by adding **WITH_ONNXRUNTIME** flag in CMake command.

Using ORT wrapper the inference time for _resnet50.onnx model_ has come to _**~7ms**_ from _**~14ms**_.
Also, we are able to run models like `ssd_mobilenet_v1.onnx`.
### Pull Request Readiness Checklist

See details at https://github.com/opencv/opencv/wiki/How_to_contribute#making-a-good-pull-request

- [x] I agree to contribute to the project under Apache 2 License.
- [x] To the best of my knowledge, the proposed patch is not based on a code under GPL or another license that is incompatible with OpenCV
- [x] The PR is proposed to the proper branch
- [x] There is a reference to the original bug report and related work
- [x] There is accuracy test, performance test and test data in opencv_extra repository, if applicable
      Patch to opencv_extra has the same branch name.
- [x] The feature is well documented and sample code can be built with the project CMake

samples/dnn/segmentation.cpp

@@ -257,6 +257,7 @@ int main(int argc, char **argv)
         //! [Set input blob]
         net.setInput(blob);
         //! [Set input blob]
+        int64 t0 = getTickCount();
 
         if (modelName == "u2netp")
         {
@@ -291,9 +292,7 @@ int main(int argc, char **argv)
         }
 
         // Put efficiency information.
-        vector<double> layersTimes;
-        double freq = getTickFrequency() / 1000;
-        double t = net.getPerfProfile(layersTimes) / freq;
+        double t = (getTickCount() - t0) * 1000.0 / getTickFrequency();
         string label = format("Inference time: %.2f ms", t);
         Rect r = getTextSize(Size(), label, Point(), fontFace, fontSize, fontWeight);
         r.height += fontSize; // padding