Project Guideline is an innovative initiative aimed at enhancing the independence of individuals with visual impairments. It leverages on-device machine learning on Google Pixel phones to enable users to walk or run independently. The system includes a waist-mounted phone, a pedestrian pathway guideline, audio cues, and obstacle detection. The technology behind Project Guideline utilizes ARCore for tracking, a segmentation model for detecting the guideline, and a depth model for identifying obstacles. This groundbreaking solution marks a significant advancement in assistive technology and represents a commitment to inclusivity and innovation.
Project Guideline: Revolutionizing Accessibility with On-Device Machine Learning for Independent Mobility
Researchers have developed Project Guideline, an innovative solution to empower individuals with visual impairments to walk or run independently. By leveraging on-device machine learning (ML) on Google Pixel phones, this groundbreaking project combines audio cues, obstacle detection, and a designated guideline on a pedestrian pathway to guide users safely through the physical world.
Key Features and Technology
Project Guideline utilizes on-device ML tailored for Google Pixel phones, departing from traditional methods that rely on external guides or guide animals. The technology behind the project includes:
– ARCore: Estimates the user’s position and orientation as they navigate the designated path.
– DeepLabV3+: Segmentation model that detects the guideline, generating a binary mask outlining its trajectory.
– Monocular depth ML model: Identifies obstacles, such as people, vehicles, and posts, by discerning their depth.
– Low-latency audio system: Delivers real-time audio cues to guide the user effectively.
How It Works
The core platform of Project Guideline is crafted using C++ and integrates essential libraries like MediaPipe. ARCore estimates the user’s position and orientation, while the segmentation model generates a 2D map of the guideline’s trajectory. The control system dynamically selects target points on the line, providing a navigation signal that considers the user’s current position, velocity, and direction. Obstacle detection, facilitated by a depth model trained on a diverse dataset, adds an extra layer of safety.
Value and Impact
Project Guideline represents a transformative stride in computer vision accessibility, offering a holistic solution that combines machine learning, augmented reality technology, and audio feedback. By open-sourcing the project, Google emphasizes its commitment to inclusivity and innovation. This initiative enhances users’ autonomy and sets a precedent for future advancements in assistive technology.
Evolve Your Company with AI
If you want to stay competitive and leverage AI for your company’s advantage, consider the Open Source Release of Project Guideline. Here are some practical steps to evolve your company with AI:
1. Identify Automation Opportunities: Locate key customer interaction points that can benefit from AI.
2. Define KPIs: Ensure your AI endeavors have measurable impacts on business outcomes.
3. Select an AI Solution: Choose tools that align with your needs and provide customization.
4. Implement Gradually: Start with a pilot, gather data, and expand AI usage judiciously.
For AI KPI management advice and continuous insights into leveraging AI, connect with us at hello@itinai.com. Discover how AI can redefine your sales processes and customer engagement with the AI Sales Bot from itinai.com/aisalesbot, designed to automate customer engagement 24/7 and manage interactions across all customer journey stages.
