vijpandaturtle/hydranet-autonomous-driving
A multi-task learning algorithm for autonomous driving tasks
This project helps self-driving car engineers and researchers by simultaneously analyzing road scenes for object recognition and depth perception. It takes raw camera footage or images as input and generates two outputs: a segmented image outlining different elements like roads, pedestrians, and vehicles, along with a depth map showing how far away objects are. Autonomous vehicle perception specialists can use this to develop or improve their systems.
No commits in the last 6 months.
Use this if you need to perform both semantic segmentation (identifying objects) and depth estimation (measuring distances) on visual data for autonomous driving applications.
Not ideal if you require highly accurate, production-ready segmentation output, as the current segmentation results are noted as noisy.
Stars
12
Forks
6
Language
Jupyter Notebook
License
—
Category
Last pushed
Nov 24, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/vijpandaturtle/hydranet-autonomous-driving"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
carla-simulator/carla
Open-source simulator for autonomous driving research.
OpenHUTB/hutb
人车模拟器
thomasfermi/Algorithms-for-Automated-Driving
Each chapter of this (mini-)book guides you in programming one important software component for...
ProjectNeura/LEADS
Enable your racing car with powerful, data-driven instrumentation, control, and analysis...
deepdrive/deepdrive
Deepdrive is a simulator that allows anyone with a PC to push the state-of-the-art in self-driving