Hi ! A new twist on these days demos, this time: Open a camera feedConvert each frame to grayscaleUse a hue mask to resalt colors, Blue and Red Here is a live sample from my office. Note: I created a mask that identifies the Captain America shield, SpyderGwen poster and Ahsoka frame, but it’s missing…… Continue reading #OpenCV – Convert camera feed 🎦 to Grayscale and resalt Blue 🔵 and Red ❤️
Hi ! A new twist on these days demos, based on a request from an online friend. Let’s remove and replace the background from our camera feed using a video. For this demo, I’m using the “Black Adam – Official Trailer 1”. And the output is kind of funny. Hey, funny scenario, and if you…… Continue reading #OpenCV – Replace background with video in camera feed 🎦 (Black Adam ⚡)
Hi ! Yesterday I wrote a post about how to remove the background from my camera feed. To remove the background, I used a python library “cvzone”. While talking with some friends, someone asked about using some of the out-of-the-box features included in OpenCV, like MOG2 or KNN. So I read a little about them…… Continue reading #OpenCV – Background Subtraction in a camera feed 🎦 using MOG2
Hi ! Yesterday I share 10 lines of code to adddress this very simple scenario: Load and image and remove the background. Today I’ll add a few extra lines, and I’ll remove the background from my camera feed. It’s fun to see how the Captain America shield was included in the cropped polygon 😁 And…… Continue reading #OpenCV – Remove the background in your camera feed 🎦
Hi ! In my previous post I wrote How to create a custom dataset with images to be used on a Azure Machine Learning Designer project. How to use the custom data set and how to train an image classification model. How to publish the model to be used as a WebService / HTTP REST…… Continue reading #AzureML – Sample 🐍 Python app using a WebCam to perform Image Analysis from an image classification AzureML HTTP REST Endpoint
Hi ! Let’s start with some posts using reTerminal with a very simple scenario: Install TensorFlow and Code on reTerminal to run an object recognition app. The desired output is something similar to this one. Live demo in a tweet ! https://twitter.com/elbruno/status/1481002326110445572?s=20 And let´s start with the base commands to install Visual Studio Code. Oficial…… Continue reading #reTerminal – Installing TensorFlow, @Code and recognizing 🐿️🐺 using a Camera 🤳
Hi ! Let’s start with some posts using reTerminal with a very simple scenario: Connect a Camera to the device and show the camera feed in reTerminal display The output is something similar to this one. And let´s start with the base code to run this, based on my previous posts on OpenCV (see references)…… Continue reading #reTerminal – Installing OpenCV, and using a USB WebCam 🤳
Hi ! Quick Friday Tip: How to add a new camera to your PC using an old Android phone. No wires required. So, In my device demos I usually have my main camera with my 😁, and I have a 2nd USB cam to show specific demos or devices. I had a green screen on…… Continue reading #OBS – Use an Android phone 🤳 as an external webcam 🎦. No cables required !
Hi ! LearnOpenCV is an amazing resource to learn about OpenCV. And, it has lot of scenarios of real life problem solved with OpenCV. Most of the samples are in C++ or Python, so I decided to pick one related to pose estimation, and using .Net 5 in a Winforms App, build something like this:…… Continue reading #dotnet – Pose detection from the 🎦 camera feed using #OpenCV and #net5. Home-made #kinect!
Hi ! So I was browsing in the OpenCV documentation and I find a nice sample that uses opencv_dnn module for image classification by using GoogLeNet trained network from Caffe model zoo. So I give it a try, and get a decent .Net 5 Winforms App running at ~30 FPS. The model was trained with…… Continue reading #dotnet – GoogleNet detection from the 🎦 camera feed using #OpenCV and #net5. Bonus: C++ to C# time!