Technology and circuit boards

For Developers & Builders

The Technical
Deep Dive

Edge AI hardware, computer vision frameworks, vision-sensor fusion architecture, and the trade-offs that matter. Everything from the research distilled into actionable engineering decisions.

Edge Hardware

Choosing Your Processing Board

Four realistic options for real-time pose estimation at the edge. Prototype budget: $130-480 depending on path.

Google Coral Dev Board

$99-129
4 TOPSPower: Low

Best for: Consumer yoga coach, single camera, lowest BOM

Ecosystem: TF-Lite + Edge TPU, smaller community

Best for shipping a consumer product fast and cheap

NVIDIA Jetson Orin Nano

$249
67 INT8 TOPSPower: Medium

Best for: Max developer velocity, broad model support

Ecosystem: CUDA, TensorRT, DeepStream, PyTorch — massive community

Best for prototyping and developer velocity

TI TDA4VM

$249
8 TOPSPower: Low

Best for: Industrial, multi-camera sensor fusion, long-term availability

Ecosystem: TI Edge AI Studio, smaller community, niche tooling

Best for productized embedded systems at scale

Luxonis OAK-D Lite

$149-170
~4 TOPSPower: Low

Best for: Plug-and-play AI camera with built-in stereo depth

Ecosystem: DepthAI APIs, Python-first, USB interface

Best middle ground — camera + compute in one device

CV Frameworks

Pose Estimation Options

MediaPipe

Open-Source33 landmarks>30 FPS
Strengths: Optimized for mobile edge, Google-backed, BlazePose architecture
Limitations: Single-person only, struggles with heavy occlusion

OpenPose

Research-Grade20/20 mappingGPU-dependent
Strengths: Multi-person detection, well-cited research baseline
Limitations: Massive model, impossible on mobile, drains battery instantly

YOLO v5/v7/X

Open-Source17 keypointsReal-time
Strengths: Fast posture classification, good for geometric slope validation
Limitations: Fewer keypoints than specialized pose models

Kemtai SDK

Proprietary44 motion pointsClinical-grade
Strengths: FDA pathway, MSK therapy, connected coaching built-in
Limitations: Licensing fees, proprietary ecosystem lock-in

asensei SDK

ProprietaryClinical-gradeReal-time
Strengths: Clinical accuracy, connected coaching logic included
Limitations: Licensing cost, ties you to their ecosystem

Architecture Decisions

The Trade-Offs That Matter

Green AI vs. Red AI

The computational complexity vs. accuracy trade-off that defines your hardware choice and user experience.

Green AI (Pragmatic)
  • TwinEDA, MediaPipe achieve ~identical accuracy at <50% compute
  • Prevents device overheating and battery drain on consumer hardware
  • < 100 Giga-FLOPs — runs on Coral, phone, or Raspberry Pi
Red AI (Precision)
  • BabyPoseNet, clinical models require >100 Giga-FLOPs
  • Necessary for FDA Class II MSK therapy (Kemtai, Exer AI)
  • 44-point tracking with 2cm joint deviation accuracy

Camera-Only vs. Vision-Sensor Fusion

Whether to rely purely on cameras or combine them with textile-integrated sensors.

Camera-Only
  • Most accessible — any smartphone becomes a coaching device
  • Engineering Brain pragmatism: physical sensors = mechanical complexity
  • Early hardware-heavy tracking attempts all failed commercially
Vision-Sensor Fusion
  • Textile IMUs (Nadi X, SeamFit) provide ground-truth 3D joint angles
  • Solves occlusion permanently — data flows regardless of camera angle
  • Apparel becomes a "ground-truth suit" for training vision models

Specialized vs. Mainstream Hardware

The developer velocity vs. production scalability debate.

Mainstream (Jetson, Coral)
  • Massive community, tutorials, Stack Overflow answers
  • Easier to hire engineers and ship MVPs quickly
  • Comprehensive software stacks (CUDA, TensorRT, TF-Lite)
Specialized (TDA4VM)
  • Low-power, highly stable, designed for embedded production
  • Multi-camera sensor fusion at scale
  • TI long-term availability for hardware supply chain

Clinical Pathway

From Consumer App to Medical Device

The engineering requirements change dramatically when targeting FDA Class II registration. Here's what the research surfaced.

Algorithmic Bias

Train on diverse datasets — body types, skin tones, lighting conditions. A model that works for one demographic is clinically useless.

False Positive Risk

Telling a patient their form is perfect when it isn't can cause severe injury. Implement human-in-the-loop review for high-risk assessments.

FDA Class II Requirements

Exer AI achieved it. Kemtai is on the path. Requires absolute safety and precision — 44 motion points, 2cm deviation margin.

Proprietary vs. Open-Source

SDKs (asensei, Kemtai) give clinical accuracy out-of-box but lock you in. Open-source (YOLOv5, MediaPipe) offers freedom but massive engineering labor for scoring logic.

Build With Us

Whether you're choosing your hardware stack, evaluating CV frameworks, or planning a clinical pathway — we're assembling the team.

Join the Build