NKDr. Naveed Khan BalochAI Systems Architect
ProjectsServicesExperienceAcademia
Book a Call
ProjectsServicesExperienceAcademiaBook a Call

Computer Vision & Mobile Health AI

YogAsana AI

YogAsana AI is an intelligent mobile application that provides real-time yoga posture correction, biomechanical alignment tracking, and joint-strain detection. Using edge computer vision, it guides safer independent practice without specialized hardware, external visual sensors, or cloud video streaming.

Real-Time Pose EstimationEdge Computer VisionMobile Fitness SaaS
Discuss a Similar Project
YogAsana AI project interface
Client TypeHealthTech startups, digital wellness platforms, virtual personal trainers, and solo yoga practitioners
RoleAI Systems Architect, Mobile CV Engineer, and Flutter Developer
TimelineFunctional MVP and production-ready pipeline
StatusLive demo and edge pipeline deployed

Value Story

Real-time alignment assistance built for personal practice.

Business Problem

Incorrect form risks long-term musculoskeletal strain

Yoga practitioners often practice independently without expert supervision. Poor form during complex postures such as Trikonasana or Chaturanga can lead to joint misalignment, spinal stress, and acute ligament injuries.

Product Strategy

On-device biomechanical pose estimation

The solution runs real-time skeleton tracking directly on mobile hardware, calculating joint-angle accuracy against anatomical baselines to provide immediate visual and audio alignment cues.

Commercial Story

Accessible, private, hardware-free wellness

Edge inference on the smartphone camera feed removes the need for expensive motion-capture wearables while keeping visual data on the user's device.

My Contribution

From skeletal keypoint inference to smooth mobile UI feedback.

Engineered hybrid pose-estimation pipelines balancing MediaPipe and OpenPose topologies for accurate skeletal keypoint inference.

Built real-time angular analysis algorithms to evaluate joint alignment and movement tolerances during live poses.

Implemented local mobile edge-inference routines in Flutter to eliminate server-side video-streaming latency.

Designed low-latency visual overlays and contextual audio alerts for mid-session posture correction.

Product Capabilities

What the user actually gets

Real-time skeleton tracking

Detects 33+ anatomical keypoints with continuous tracking designed for partial occlusion and complex body positions.

Angle precision and form scoring

Compares shoulder, hip, knee, and ankle vectors with target geometric templates to calculate a live posture-alignment score.

Active injury prevention

Highlights vulnerable joints when knee deflection, lumbar extension, or another tracked angle moves outside configured safety thresholds.

Voice-guided form feedback

Context-aware audio cues explain which movement to adjust while the user remains focused on the pose.

System Architecture

Camera capture to instant pose feedback flow

01

Camera Stream Layer captures high-frame-rate video through Flutter camera-controller bindings.

02

Frame Preprocessing and ROI Layer crops, normalizes, and isolates regional bounding boxes for efficient inference.

03

Edge Keypoint Engine executes lightweight MediaPipe and OpenPose models on local mobile acceleration hardware.

04

Biomechanical Logic Layer calculates Euclidean vectors, joint-angle offsets, and posture-hold stability scores.

05

Visual Overlay and Feedback Layer renders skeletal guidance and delivers contextual audio and haptic cues.

Outcomes

What this proves

  • Built an on-device computer vision workflow capable of real-time pose estimation at 30+ FPS on mobile hardware.
  • Mitigated visual privacy risks by running inference locally without cloud video transfer.
  • Delivered an end-to-end mobile architecture combining biomechanical pose calculations with smooth UI rendering.
  • Created a scalable foundation for fitness, rehabilitation, and athletic movement-tracking applications.

Technology

Core stack

FlutterMediaPipeOpenPoseDartTensorFlow LiteComputer VisionMobile Edge AI

Work together

Need an AI vision workflow that turns camera feeds into real-time operational insights?

I can help define the edge computing architecture, optimize neural network inference on mobile devices, and build production-ready applications for real-world interactions.

Schedule a Call

More projects

Related case studies

Research Automation

AI Research Reviewer

Researchers upload manuscripts and receive structured AI feedback before journal, conference, or supervisor submission.

Voice AI for Restaurants

Freja AI

Restaurant teams use AI voice ordering to answer calls, capture multilingual orders, and route kitchen-ready tickets.

Adaptive Learning Platform

LearnoviaX

Personalized learning paths, quizzes, progress tracking, and AI tutor agents guide students toward measurable mastery.

Hiring Intelligence

Interveuu

Recruiters manage job posts, screen resumes, run AI interviews, and review candidate reports from one hiring workspace.

Healthcare AI

ClinIQ Assist

Source-grounded clinical knowledge, speech input, and safety-aware summaries come together for clinician support workflows.

Hospitality SaaS

Bokafy

Conversational booking flows connect guest reservations, real-time availability, and staff table management.