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

SIMD-accelerated computer vision on a $2 microcontroller

shraiwi.github.io

Post reply on HN
Print view View original

31–40 of 60 posts

Re: SIMD-accelerated computer vision on a $2 microcontroller

#31

Post by the__alchemist »

Qwuke wrote: post #30
ladyanita22 wrote: post #25

Anyone with experience on Rust for ESP32 controllers could chime in on whether this is feasible on rust as well?

Compared to ESP8266, there's generally pretty good ESP32 support for Rust, but you'll likely need to use in your C++ toolchain if you want to use the standard library. no-std in Rust for ESP32 isn't terrible in my experience, though, just not as fleshed out - particularly for hooking into components like wifi/networking and probably a camera as well. Like the other commenter said, there's plenty of support for SIMD a…

You can actually use the IDF system in Rust to use the std lib, at least on ESP32-C3. Probably others too.

If you are on Windows, you will need to place the project folder at the top level drive directory, and there are other quirks as well, but it works.

Re: SIMD-accelerated computer vision on a $2 microcontroller

#32

Post by surfingdino »

mppm wrote: post #24
DeathArrow wrote: post #17

>For silicon that's cheaper than the average coffee, that's pretty cool. Maybe it's not the chip that it's too cheap. Maybe it's the coffee that's too expensive.

OTOH, I've been waiting for disposable coffee cups with OLED-based video ads ever since Minority Report. But tech progress is just too damn slow :P

Almost there... https://www.moveelectric.com/e-motorbikes/super-soco-aims-se...

Re: SIMD-accelerated computer vision on a $2 microcontroller

#33

Post by thrtythreeforty »

duskwuff wrote: post #7
restricted_ptr wrote: post #2

I wonder if ESP32 has VLIW slots and a tighter instruction packaging is possible?

Neither Xtensa nor RISC-V are VLIW architectures.

Generally speaking, this is not correct. Base Xtensa is not VLIW, but Xtensa's various vector extensions do allow VLIW instructions, collectively called "FLIX."

It is doubtful that ESP32's Xtensa is VLIW-capable, though. Presumably their compiler would emit FLIX instructions if it were.

Re: SIMD-accelerated computer vision on a $2 microcontroller

#34

Post by dansitu »

If you're interested in this stuff and wanna try it yourself, check out our product, Edge Impulse:

https://edgeimpulse.com/ai-practitioners

We work directly with vendors to perform low level optimization of deep learning, computer vision, and DSP workloads for dozens of architectures of microcontrollers and CPUs, plus exotic accelerators (neuromorphic compute!) and edge GPUs. This includes ESP32:

https://docs.edgeimpulse.com/docs/edge-ai-hardware/mcu/espre...

You can upload a TensorFlow, PyTorch, or JAX model and receive an optimized C++ library direct from your notebook in a couple lines of Python. It's honestly pretty amazing.

And we also have a full Studio for training models, including architectures we've designed specifically to run well on various embedded hardware, plus hardware-aware hyperparameter optimization that will find the best model to fit your target device (in terms of latency and memory use).

Re: SIMD-accelerated computer vision on a $2 microcontroller

#35

Post by ska »

implements wrote: post #21
shraiwi wrote: post #4

Earlier quoted context omitted.

Thanks for reading! > What are some use cases for FAST? The FAST feature detector is an algorithm for finding regions of an image that are visually distinctive, which can be used as a first step in motion tracking and SLAM (simultaneous localization and mapping) algorithms typically seen in XR, robotics, etc. > Is there TPU-like functionality in anything in this price range of chips yet? I think that in the case of t…

> The FAST feature detector is an algorithm for finding regions of an image that are visually distinctive, … Is that related to ‘Energy Function’ in any way? (I ask because a long time ago I was involved in an Automated Numberplate Reading startup that was using an FPGA to quickly find the vehicle numberplate in an image)

What you are thinking of operates at a different level of abstraction. Energy functions are a general way of structuring a problem, used (sometimes abused) to apply an optimization algorithm to find a reasonable solution for it.

FAST is an algorithm for efficiently looking for "interesting" parts (basically, corners) of an image, so you can safely (in theory) ignore the rest of it. The output from a feature detector may end up contributing to an energy function later, directly or indirectly.

Re: SIMD-accelerated computer vision on a $2 microcontroller

#37

Post by TheMagicHorsey »

dansitu wrote: post #34

If you're interested in this stuff and wanna try it yourself, check out our product, Edge Impulse: https://edgeimpulse.com/ai-practitioners We work directly with vendors to perform low level optimization of deep learning, computer vision, and DSP workloads for dozens of architectures of microcontrollers and CPUs, plus exotic accelerators (neuromorphic compute!) and edge GPUs. This includes ESP32: https://docs.edgeimp…

Yo! This is awesome stuff!

Re: SIMD-accelerated computer vision on a $2 microcontroller

#38

Post by dansitu »

TheMagicHorsey wrote: post #37
dansitu wrote: post #34

If you're interested in this stuff and wanna try it yourself, check out our product, Edge Impulse: https://edgeimpulse.com/ai-practitioners We work directly with vendors to perform low level optimization of deep learning, computer vision, and DSP workloads for dozens of architectures of microcontrollers and CPUs, plus exotic accelerators (neuromorphic compute!) and edge GPUs. This includes ESP32: https://docs.edgeimp…

Yo! This is awesome stuff!

Thank you! We're trying to bring embedded ML in reach of all engineering teams and domain experts.

Previously you needed a crazy mixture of ML knowledge and low-level embedded engineering skills even to get started, which is not a common occurrence!

Re: SIMD-accelerated computer vision on a $2 microcontroller

#39

Post by rhelz »

DeathArrow wrote: post #17

>For silicon that's cheaper than the average coffee, that's pretty cool. Maybe it's not the chip that it's too cheap. Maybe it's the coffee that's too expensive.

> Maybe it's the coffee that's too expensive.

Ha, well, there is a disturbing reason why computer vision with ultra-cheap hardware is possible: countries all over the world are buying these by the billions in order to keep an eye on their citizens :-(

Big brother is enabling incredible economies of scale....

Re: SIMD-accelerated computer vision on a $2 microcontroller

#40

Post by RobotToaster »

dansitu wrote: post #34

If you're interested in this stuff and wanna try it yourself, check out our product, Edge Impulse: https://edgeimpulse.com/ai-practitioners We work directly with vendors to perform low level optimization of deep learning, computer vision, and DSP workloads for dozens of architectures of microcontrollers and CPUs, plus exotic accelerators (neuromorphic compute!) and edge GPUs. This includes ESP32: https://docs.edgeimp…

I don't think the output from this can be used in any open source project due to the community plan restrictions, FYI.
Post reply on HN