Raspberry pi YOLO v2 Object Detection

more info.

You only look once (YOLO) is a state-of-the-art, real-time object detection system.

What's New in Version 2?

YOLOv2 uses a few tricks to improve training and increase performance. Like Overfeat and SSD we use a fully-convolutional model, but we still train on whole images, not hard negatives. Like Faster R-CNN we adjust priors on bounding boxes instead of predicting the width and height outright. However, we still predict the x and y coordinates directly. The full details are in our paper.!

My Website

My Blog

Tel .[phone] ( Thailand )

[rifatmasud]

is this on pi3 or pi4? also have you tried ssd? if so what is the performance?

[EdjeElectronics]

Dang, 32 seconds to predict one image! That's slow. But this is good information to know! Thanks for the video.

[mbonuchinedu]

yolov3 is faster and more accurate. nice vid

[fergaletto]

As you can see in the video i reached 4fps with only loading the CPU to 20%, this is because I'm using an intel NCS2 to do the inference.



reagards.