Activity Recognition

Create Advanced Wearables with Activity and Gait Analysis

Miles Beyond Simple Motion Tracking
SensiML activity recognition Knowledge Packs can deliver real-time form analytics and custom motion classification for your next wearable computing application. We have developed proven models for a wide range of applications from consumer sports/fitness devices to worker safety gear and factory wearables. Using low-cost, multi-axis accelerometer and gyroscopic MEMS sensors, SensiML models can provide accurate and generalizable pattern recognition for a wide-range of motions and activities.
Proven Applications:
  • Ergonomics and worker safety
  • Fitness and sports performance
  • Animal health and wellness
  • Operations monitoring and analysis
Advanced Motion Analytics Models
SensiML has labeled motion analytics datasets available for license that can be used as provided or extended and modified to suit custom requirements.
Examples of datasets available include:
  • Running form assessment
  • Human activities of daily living
  • Ergonomics (box lifting)
  • Tennis form
  • Football tackling
  • Dog activity recognition

    and more...

Smart Boxing Glove Demo
This demo shows how a SensiML Knowledge Pack can be created to classify a variety of boxing punches in real-time. Specifically, we show the output of a Knowledge Pack trained to recognize the following punch movements:
  • Jab
  • Cross
  • Uppercut
  • Hook
  • Overhand
Platforms and Plans
SensiML offers complete Knowledge Pack development services allowing you to focus on your application. Our team can devise a customized project plan using your activity-based training data to create a tailored recognition libraries ready to drop into your application.
Platforms and Plans
For project teams with basic machine learning familiarity, desire to learn, or needing to undertake the tasks entirely in-house, SensiML offers its ML Analytics Toolkit suite. A true end-to-end workflow, SensiML Analytics Toolkit supports the complete process from data collection and labeling to Knowledge Pack generation and testing.