Erik Langskjegg's profile - activity

I understand, sorry for my lack of precision. It looks like your CUDA implementation will make a fine impact on the DNN

thanks so much, I can't wait to try out your Google project!

thanks, I can't wait to try out your Google project!

thanks! I just miss one karma point from upvoting the answer :)

I am so exited for the merging of the GSoC project enabling CUDA support in OpenCV!

However I am uncertain about the build procedure shown in this gist. I think I understand setting cmake build options like this:

cmake -D CMAKE_BUILD_TYPE=RELEASE \
  -D CMAKE_INSTALL_PREFIX=/usr/local \
  -D WITH_CUDA=ON \
  -D WITH_CUDNN=ON \

Where do I set the "following option"

OPENCV_DNN_CUDA

then?

@Yashas, I have one question about building with CUDA based on your gist. The two first points WITH_CUDA and WITH_CUDNN

Build OpenCV 4 with CUDA I am so exited for the merging of the GSoC project enabling CUDA support in OpenCV! However I

Build OpenCV 4 with CUDA I am so exited for the merging of the GSoC project enabling CUDA support in OpenCV! However I

Thank you so much! I will look into YoloV3 now, starting with Learn OpenCV

I do not need pixel-precise segmentation or advanced polygons by the way. Rectangular bounding boxes with 4 corners will

I do not need pixel-precise segmentation or advanced polygons by the way. Rectangular bounding boxes with 4 corners will

Thanks for asking @kbarni! If I can get a proof of concept running, the solution might eventually be shown on TV. The in

There is also a nice tutorial for Mask R-CNN and OpenCV on PyImageSearch

it sounds like Mask R-CNN will be your best option. If you eventually follow the example, the bounding box coordinates a

it sounds like Mask R-CNN will be your best option.

So I promised to prototype a model for object detection trained on my own labeled videos; in real time on full HD video @25 fps. I have spent quite some time learning Mask R-CNN. Now the model is running I realized that this library is too slow.

I have googled OpenCV, browsed through LearnOpenCV, searched these forums, peaked at the tutorials at opencv.org etc. I understand that using the DNN module with C++ will let me train my own model and do object detection at some frame rate.

Which OpenCV based method would you choose for training an object detection model to work @25 fps, full HD?

@kbarni, you are right, sorry. I do have my own Mask R-CNN model working offline (separate still frames). I want to d

@kbarni, you are right, sorry. I do have my own Mask R-CNN model working offline (separate still frames). I want to d

@kbarni, you are right, sorry. I do have my own Mask R-CNN model working offline (separate still frames). I want to d

@kbarni, you are right, sorry. I do have my own Mask R-CNN model working offline (separate still frames). I want to d

@kbarni, you are right, sorry. I do have my own Mask R-CNN model working. I want to detect road signs filmed from a ca

@kbarni, you are right, sorry. I do have my own Mask R-CNN model working. I want to detect road signs filmed from a ca

Sorry if I'm conceived as being lazy for asking instead of trying. I just would like a friendly heads-up if my goal is n

Based on this blog post, it looks like that specific method has an inference time of ~300 milliseconds? Does that extend

Which method for object detection at 25 fps, full HD? So I promised to prototype a model for object detection trained on

Which method for object detection at 25 fps, full HD? So I promised to prototype a model for object detection trained on

Which method for object detection at 25 fps, full HD? So I promised to prototype a model that would do object detection

Based on this blog post, it looks like that specific method has an inference time of ~300 milliseconds? Does that extend

Based on this blog post, it looks like that specific method has an inference time of ~300 milliseconds? Does that extend

Based on the blog post, it looks like that specific method has an inference time of ~300 milliseconds? Does that extend

Based on the blog post [1], it looks like that specific method has an inference time of ~300 milliseconds? Does that ext