Yolov5 into Processing Library

[Clifford]

Hi
Ive been using processing for sometime now one thing that interest me is the open cv application .

is there is some way to incorporate ultralytics Yolo5v Vision AI into Processing and make it simple to implement . lets say servo control with the Arduino Libraries.

the Yolo application I wanted to implement

GitHub - ultralytics/yolov5: YOLOv5 🚀 in PyTorch > ONNX > CoreML >...

[josephh]

Hi @Clifford,

Welcome to the forum!

You can check out this older post about YOLO detection in Processing:

YOLO object detection

Hello guys, Is there a way to do YOLO real time object detection in processing (or P5.js/processing.py) using a library like this : I already know OpenCV for computer vision but it doesn’t include object detection. Thanks

And also the deep-vision-processing library by @cansik :

Deep Vision - Machine Learning Computer Vision for Processing (Library)

Hello Together I’m happy to present you a project I’ve been working on for over a year now. With OpenCV for Processing we have a good base library for traditional image processing. However, these algorithms are more and more pushed into the background by machine learning. Therefore I started a year ago to develop a library that (mainly) uses the Deep Neural Network (DNN) module of OpenCV to bring machine learning, especially CNN into the Processing world. The library is not about training the…

[Clifford]

yes I found the library for processing Yolov4 yet to see if anyone update it for Yolov5 as im using this version

[cansik]

Is there now an “official” yolov5 implementation? I guess there was more than one repo claiming to be the next yolov5…

[cansik]

@Clifford I have implemented the Ultralytics YOLOv5 into the DeepVision library for Processing: Release Version 0.9.0 · cansik/deep-vision-processing · GitHub

It is currently not released over the contribution manager, but you can download and install it directly from the releases. There is even an example which shows how to execute YOLOv5. I would recommend to adjust the setTopK(int k) variable according to how many objects you have in your pictures (default is 100). You can read more about this in the YOLOv5 section.

At the moment implemented are the N, S, M, L and X models (640x640). But it would be simple to add custom models by exporting them to the ONNX format.