Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Supercharge your Computer Vision models with the TensorFlow Object Detection API

research.googleblog.com

Post reply on HN
Print view View original

1–10 of 66 posts

Re: Supercharge your Computer Vision models with the TensorFlow Object Detection API

#4

Post by sharemywin »

They need some kind of context input.

-GPS position, intent/goal, domain etc.

I'm at a dog show I would want breed etc.

I'm on the street I just want it come back dog maybe dangerous dog, friendly dog.

Also, would be cool/scary to just get back movable object 1, person 1, living movable object 3 etc. and if I give it multiple scenes from a video it knows person 1 is the same person 1 and if I name (them) Tony it keeps tracking tony.

Re: Supercharge your Computer Vision models with the TensorFlow Object Detection API

#6

Post by kyrra »

accountyaccount wrote: post #5

This would be great to run a security camera still feed through. It could completely eliminate false positives.

I wonder if Nest is using it with their new cam[0], as it has person alerts now (with face detection).

[0] https://nest.com/camera/meet-nest-cam-iq/

Re: Supercharge your Computer Vision models with the TensorFlow Object Detection API

#8

Post by halflings »

kyrra wrote: post #6
accountyaccount wrote: post #5

This would be great to run a security camera still feed through. It could completely eliminate false positives.

I wonder if Nest is using it with their new cam[0], as it has person alerts now (with face detection). [0] https://nest.com/camera/meet-nest-cam-iq/

They would probably use FaceNet[0] then, if they only want to detect faces, as that should give better results.

[0] https://arxiv.org/abs/1503.03832

Re: Supercharge your Computer Vision models with the TensorFlow Object Detection API

#9

Post by neuronexmachina »

sharemywin wrote: post #4

They need some kind of context input. -GPS position, intent/goal, domain etc. I'm at a dog show I would want breed etc. I'm on the street I just want it come back dog maybe dangerous dog, friendly dog. Also, would be cool/scary to just get back movable object 1, person 1, living movable object 3 etc. and if I give it multiple scenes from a video it knows person 1 is the same person 1 and if I name (them) Tony it keep…

I imagine you could use the confidence-value output of the object-detection API as input into a separate system that would also incorporate the other inputs you mention.
Post reply on HN