On-device inference and computer vision — engineering notes on running AI at the edge.
Mobile apps now depend on real-time camera pipelines more than ever. Whether you're scanning QR codes, running on-device AI, analyzing food labels, previewing AR overlays, or streaming video, smooth, uninterrupted camera frames are critical. Here's the catch: mobile devices are unpredictable. CPU spikes, GPU contention, thermal
Introduction In pet tech, the gap between something that works and something that's actually reliable usually comes down to how well the hardware reads the real world. At Hoomanely, we've spent months refining EverBowl's proximity pipeline, the system that helps our smart bowl track
Modern AI products feel personal only when they remember, that bug you were debugging yesterday, the pet profile you set up last month, the long-running coaching thread you keep coming back to. Under the hood, though, LLM inference APIs don't remember anything. Every call is a clean slate,
Most teams add AI the same way they add any new feature: ship a model, wire an endpoint, move on. A few months later, you're juggling three versions of the "scoring service," five subtly different summarizers, and a bundle of feature flags nobody fully trusts. Changing
Introduction When you look at something, your brain merges two slightly different images from your eyes to work out depth and distance without any real effort. Getting a machine to do the same thing is a lot harder. At Hoomanely, stereo vision is central to how we read depth, shape,
Vision that starts with a square At Hoomanely, we're building systems that see and understand pets, from their eyes and movement to the bowls they eat from. That means our camera pipeline needs to detect key visual cues with precision and speed, even on a small edge chip
Intro You spend weeks training a model, then realize deploying it efficiently across devices, from cloud GPUs down to a Raspberry Pi, is a whole separate problem. That's where ONNX Runtime comes in. Built by Microsoft with a large open community behind it, ONNX Runtime (ORT) is the
Intro Look at a photograph and your brain instantly works out what's near and what's far, even though the image itself is flat. Machines don't have that instinct built in. Monocular depth estimation teaches a computer to infer depth from a single camera, no
How AI models are shrinking without losing their minds. Many of our real-time models, from detecting dog motion to analyzing eating patterns, run directly on embedded systems. At Hoomanely, we pair lightweight CNNs like MobileNet with quantization and pruning to get low-latency inference without giving up reliability. Processing data locally