Show HN: I made Amazon GO with Two Nvidia Jetsons

Show HN: I made Amazon GO with Two Nvidia Jetsons(linkedin.com)

6 points by bmadduma 2 years ago | 4 comments

I replicated Amazon GO's cashier-less tech with less than $5000. Two nvidia jetson orin and 4 security cameras ( $100 each).

mtmail 2 years ago |

I was sceptical: a Linkedin post, an obfuscated (shortened) link to https://www.fixelmagic.com and on that homepage a lot of marketing speak, basically a waiting list page.

But the Linkedin post has a video! showing a shopper (you?) and the "I made ... with Two Nvidia Jetsons" is some background. Great video, great project.

bmadduma 2 years ago | |

It can be a bit of marketing. I just want to show the achievement. I bootstrapped this project with a couple of forks. As I said, I wanted to build an Amazon Go like tech with less as I don't have millions. if you are interested how I did it. We used 4 security cameras and fed camera streams to 2 Jetson Orin devices. We developed a 3D perception model to track people and generate events when people pick items from the shelf. No face detection. This is a 8x8 store mock store. hardware cost is less than $5000. The system is ready for deployment in any airport micro store or sports arena. It may be needed to fine-tune the model to fit the environment.

Bottom line, real-time computer vision applications are possible and create value without spending a lot of money.

ChathuraIM 2 years ago |

Cool! Very Interesting. Do customers get real-time checkout updates?

prodevz 2 years ago |

interesting stuff! have you considered the possibility of this tech in other domains except for retail?