Skip to content

Latest commit

Β 

History

3 Commits

Folders and files

NameName
Last commit message
Last commit date
Β 
Β 
Β 
Β 
Β 
Β 

Repository files navigation

Adaptive Shadow Detection for Assistive Navigation (ASDS)

πŸ“Œ Overview

Adaptive Shadow Detection System (ASDS) is a context-aware, lightweight neural network framework designed to improve assistive navigation for visually impaired individuals.

The system reduces false positives caused by shadows and enables real-time deployment on mobile devices using efficient MobileNet-inspired architecture.


πŸ“„ Research Paper

The complete research paper is available here:

πŸ“Ž Download Research Paper


πŸš€ Key Features

  • Lightweight MobileNet-inspired architecture
  • Context-aware environmental classification
  • Adaptive threshold learning
  • Temporal smoothing for stability
  • Physics-informed shadow validation
  • 8-bit quantized mobile optimization
  • Real-time performance (22 FPS on Snapdragon 778G)

πŸ— System Architecture

The ASDS pipeline includes:

  1. Multi-scale Feature Extraction
  2. Context Analysis Module
  3. Shadow Prediction Engine
  4. Temporal Learning Module
  5. Mobile-Optimized Real-time Processing

πŸ“Š Performance Highlights

Metric Value
Accuracy 0.8892
F1-score 0.8564
AUC 0.9178
FPS (Mobile) 22 FPS
Model Size ~7.3 MB

πŸ“‚ Dataset Used

  • ISTD (Image Shadow Triplets Dataset)
  • UCF Shadow Dataset

πŸ›  Technologies Used

  • Python 3.8
  • PyTorch
  • ONNX
  • Mobile 8-bit Quantization
  • Ubuntu 18.04
  • Snapdragon 778G (Deployment)

πŸ‘©β€πŸ’» Authors

  • Paulami Sahu
  • Kritika Varyani
  • Mallu Vineela Reddy

Vellore Institute of Technology, India


About

Adaptive Shadow Detection for Assistive Navigation: A Context- Aware Approach Using Lightweight Neural Networks

Resources

Stars

1 star

Watchers

0 watching

Forks

Releases

Packages

Contributors

Languages