Skip to main content

Gavin Gong

a.k.a. VisualDust

I'm a first year PhD student in Computer Science, NCSU (North Carolina State University), being an apprentice of Dr. Wujie Wen. I got my bachelors degree from GUET (Guilin University of Electronic Technology). I was previously on computer vision, recently I'm on joint optimization on privacy preserving AI computing on large language model things. I consist of PyTorch, CUDA, dotnet, and LaTeX.

Blogs

Blogs

Random notes about developing, programming or argorithm related theory. Also some useless anecdotes.

CV Tutorial

CV Tutorial

Self taught learning materials by me and my friends. Focusing on Deep learning technique for Computer Vision.

CV Paper Reading Notes

CV Paper Reading Notes

Random paper reading, where some interesting papers about Computer Vision were recapitulated and analyzed.

Recently Maintaining

NEETBOX

NEETBOX is a great tool for Logging/Debugging/Tracing/Managing/Facilitating long-running python code, especially for deep learning training. NEETBOX is a all-in-one python package consists of client, server and frontend. NEETBOX provides easy python APIs and launches a dashboard for monitoring all the connected projects.

1 of 2

Cool Things

  • Network based inference

    The inference results and images of the assisted driving system are distributed through the network and are compatible with various platforms through web technology. This allows assisted driving edge computing devices to be deployed outside of existing vehicle-mounted terminals. Use a tablet instead when you don't have a screen on car.

  • Blind Spot Visualization

    Visualization on blind spots keeps the surroundings safe. The proposed approach allows lidar data and input from ultrasonic sensors. Both hardware and software are implemented from scratch. The system read sensor values within a optimized latency to to ensure real-time speed. We tried a more intuitive visualization method and corresponding UI design.

  • Illegal Driving Behavior Detection

    A set of integration for detecting illegal driving behaviors from edge computing devices, cloud services to mobile apps developed by us. The driver's facial key point features are used to judge dangerous driving behavior. Results are recorded on server and delivered to user's phone app that users can correct their behaviors on their own.

  • Road scene seg on embedded device

    Light weight yet accurate semantic segmentation model designed and trained for road scence. The proposed model is applied for scene understanding and drivable area detection. The proposed model achieved smooth floating-point precision inference on edge computing device NVIDIA Jetson NX with the speed of 25FPS.

  • Network based inference

    The inference results and images of the assisted driving system are distributed through the network and are compatible with various platforms through web technology. This allows assisted driving edge computing devices to be deployed outside of existing vehicle-mounted terminals. Use a tablet instead when you don't have a screen on car.

1 of 5