I use Edge impulse for object detection.
I need some informations for my thesis and here comes my questions:
Which algorithm are used for the object detection? I have been searching for information all day but unfortunately have not found anything. Which ML typ and algorithm are used for it? unsuperviced and
dimensionality reduction algorithms?
And do you use SSD? Is this correct?
thank you for your help
First, edge impulse object detection is based on supervised learning since you need to upload some training data to train your model.
The detector uses transfer learning based on the SSD MobileNet V2 architecture.
You can further tune the model however you want using the Keras (expert) mode.
Let me know if this helps and if you have any other question.
Hi @oduor_c ,
But if i use the default settings it uses the ssd?
I don’t use the expert mode, I’m more like a beginner on object detection😄
Thanks for your help
Hi @Patricksch ,
Yes, by default it uses the Mobilenet SSD.
Thanks for your quick reply😀