enginBozkurt/CarlaSimulatorDataCollector
Saving incoming camera sensor images data as Numpy arrays to generate ground truth data for semantic segmentation
This project helps self-driving car developers and researchers create high-quality training data for semantic segmentation models. It efficiently captures camera, depth, and semantic segmentation ground truth data directly from the CARLA simulator. The output is a series of large NumPy arrays (.npy files) that are ready for neural network training, allowing for faster processing than traditional image file saving.
No commits in the last 6 months.
Use this if you are developing or training deep learning models for autonomous vehicles and need to quickly generate synchronized, ground truth semantic segmentation data from the CARLA simulator.
Not ideal if you need to capture data from a physical car or a simulator other than CARLA 0.8.4.
Stars
27
Forks
8
Language
Jupyter Notebook
License
—
Category
Last pushed
Apr 17, 2019
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/enginBozkurt/CarlaSimulatorDataCollector"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
autowarefoundation/autoware_vision_pilot
Free self-driving car stack - fully open-source ADAS and autonomous driving system
noshluk2/ROS2-Self-Driving-Car-AI-using-OpenCV
ROS2 Self Driving Car using Deeplearning and Object Tracking through openCV
visionpilot-project/VisionPilot
Open-source modular autonomous driving simulation platform with computer vision, deep learning,...
Lyric0620/ETSAuto
🚚 ETSAuto is an Advanced driver Assistance System applied in Euro Truck Simulator 2, performing...
jefmenegazzo/Intelligent-Vehicle-Perception-Based-on-Inertial-Sensing-and-Artificial-Intelligence
Intelligent Vehicle Perception Based on Inertial Sensing and Artificial Intelligence