Hardware Podcasts

69. Feet Pics Saving The Planet & Fly Eye Inspired AI

The Next Byte Podcast · 10 May 2022 · 31m

What this episode covers

Hosts Daniel Scott Mitchell and Farbod Moghaddam discuss two computer vision applications: Snapfeet's technology for reducing footwear returns and a bio-inspired drone detection system. They detail how Snapfeet uses photogrammetry and machine learning to create 3D foot models for better fit, partnering with brands like Hugo Boss. They then explain how researchers from the University of South Australia and Flinders University use hoverfly-inspired algorithms to detect drones by converting audio data into visual heat maps.

Most relevant to

early-stage companies

Topics

Mentioned

Companies
Snapfeet, University of Cambridge, Hugo Boss, University of South Australia, Flinders University, Carnegie Mellon, Wevolver

Related episodes from other shows

Other shows on the same ground, closest first.

  • Hard Tech Podcast · 1h 32m

    Alex Villanueva: Asteroid Mining, Virtual Apparel Fitting, Biomimicry Inspired Tech | Hard Tech Podcast #17

    Alex Villanueva, founder and CEO of Eclo, explains how his AI platform reduces apparel returns by predicting shoe fit through a smartphone foot scanner and user preferences. He details the technical challenges of capturing 3D foot data and the business insight that increasing conversion rates is more valuable to retailers than just reducing returns. Villanueva also reflects on his graduate research building biomimetic robotic jellyfish at Virginia Tech and his internship at NASA working on pulse plasma thrusters.

    Connected products & IoTAI & machine learning
    8 chapters

  • Embedded.fm · 1h 07m

    253: We'll Pay Them in Fun (Repeat)

    Kathleen Tuite, a software engineer at GrokStyle, discusses computer vision, photogrammetry, and the design of 'games with a purpose' like Duolingo. She explains how GrokStyle uses visual search to identify furniture styles and powers the IKEA Place augmented reality app. Tuite also details her graduate research on structure-from-motion and her efforts to build a technical community for women in Santa Cruz through the Pi Ladies meetup.

    AI & machine learningSensors & measurement in products
    6 chapters

  • Embedded.fm · 1h 07m

    253: We'll Pay Them in Fun

    Kathleen Tuite, a software engineer at GrokStyle, discusses computer vision, augmented reality, and gamification. She explains how GrokStyle uses visual search to identify furniture for clients like IKEA, powering the IKEA Place app. Tuite also details her work on photogrammetry, structure-from-motion, and 'games with a purpose' like the ESP game and Duolingo, which leverage human input to train AI models. Finally, she describes her efforts to build community through the Santa Cruz Piladies meetup.

    Embedded firmwareAI & machine learning
    6 chapters

  • IoT For All Podcast · 24m

    AI & Computer Vision’s Role in IoT | Drover AI's Alex Nesic

    Alex Nesic, Co-Founder and Chief Business Officer of Drover AI, explains how the company uses edge-based computer vision and AI to solve GPS inaccuracies in shared micromobility fleets. He details the PathPilot module, which provides contextual location awareness to ensure regulatory compliance and safety for e-scooters and bikes. Nesic also discusses the strategic decision to launch as a retrofit module before integrating directly into vehicle designs to reduce costs and accelerate time-to-market.

    AI & machine learningConnected products & IoT
    7 chapters

  • Embedded.fm · 1h 11m

    161: Magenta Doesn't Exist

    Kat Scott, a senior software engineer at Planet and co-author of 'Practical Computer Vision with SimpleCV', explains the fundamentals of computer vision, emphasizing that it is largely about discarding irrelevant data to find specific signals. She details the challenges of industrial computer vision, noting that consistent lighting and constrained environments are critical for success, and warns that achieving high accuracy in machine learning requires exponentially more data for each decimal place of improvement. Scott also discusses the technical pipeline behind real-time face filters like those on Snapchat, which involve face detection, 3D mesh fitting, and reprojection, and advises engineers to use tools like OpenCV and ROS rather than reinventing the wheel.

    AI & machine learningIndustrial & consumer product design
    10 chapters

The summary, chapters and topics are generated from the episode’s audio by this directory, not written by The Next Byte Podcast. The episode itself belongs to its publisher.