#500 · Primary category： Computer Vision
TensorFlowAndroidDemo
TensorFlow Android demo: lane line, vehicle, face, action, skeleton recognition and detection, smoking, phone call, eyes closed/open.
Project last updated：06/16/19
GitHub Stars
747
Forks
206
Contributors
3
License
Other
Why we included this project
Anyone who has tried to lift the official TensorFlow demo code into their own Android app knows how much wiring that takes. This project does the work in one place: it runs several vision models through the Camera2 API, including lane and preceding-vehicle detection with simple logic that flags lane departure or a car getting too close, classifiers for smoking, phone use, and open or closed eyes, and a pose-estimation model that maps 19 body keypoints. The author is upfront about the rough edges, noting that mobile TensorFlow ran on CPU only at the time and that the skeleton model needs three layers of tensor transforms before it works. Treat it as a working reference and starting point, not a production SDK.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)