All Projects → Ozzyz → carla-data-export

Ozzyz / carla-data-export

Licence: MIT license
A simple tool for generating training data from the Carla driving simulator

Programming Languages

python
139335 projects - #7 most used programming language
shell
77523 projects

Projects that are alternatives of or similar to carla-data-export

Carla
Open-source simulator for autonomous driving research.
Stars: ✭ 7,012 (+14819.15%)
Mutual labels:  autonomous-driving, carla-simulator
MotionNet
CVPR 2020, "MotionNet: Joint Perception and Motion Prediction for Autonomous Driving Based on Bird's Eye View Maps"
Stars: ✭ 141 (+200%)
Mutual labels:  autonomous-driving
Master-Thesis
Deep Reinforcement Learning in Autonomous Driving: the A3C algorithm used to make a car learn to drive in TORCS; Python 3.5, Tensorflow, tensorboard, numpy, gym-torcs, ubuntu, latex
Stars: ✭ 33 (-29.79%)
Mutual labels:  autonomous-driving
highway-path-planning
My path-planning pipeline to navigate a car safely around a virtual highway with other traffic.
Stars: ✭ 39 (-17.02%)
Mutual labels:  autonomous-driving
dgp
ML Dataset Governance Policy for Autonomous Vehicle Datasets
Stars: ✭ 65 (+38.3%)
Mutual labels:  autonomous-driving
FLAT
[ICCV2021 Oral] Fooling LiDAR by Attacking GPS Trajectory
Stars: ✭ 52 (+10.64%)
Mutual labels:  autonomous-driving
PiP-Planning-informed-Prediction
(ECCV 2020) PiP: Planning-informed Trajectory Prediction for Autonomous Driving
Stars: ✭ 101 (+114.89%)
Mutual labels:  autonomous-driving
efficient online learning
Efficient Online Transfer Learning for 3D Object Detection in Autonomous Driving
Stars: ✭ 20 (-57.45%)
Mutual labels:  autonomous-driving
pillar-motion
Self-Supervised Pillar Motion Learning for Autonomous Driving (CVPR 2021)
Stars: ✭ 98 (+108.51%)
Mutual labels:  autonomous-driving
self-driving-ish computer vision system
This project generates images you've probably seen in autonomous driving demo. Object Detection, Lane Detection, Road Segmentation, Depth Estimation using TensorRT
Stars: ✭ 254 (+440.43%)
Mutual labels:  autonomous-driving
pyMHT
Track oriented, multi target, multi hypothesis tracker
Stars: ✭ 66 (+40.43%)
Mutual labels:  autonomous-driving
AVP-SLAM-PLUS
An implementation of AVP-SLAM and some new contributions
Stars: ✭ 371 (+689.36%)
Mutual labels:  autonomous-driving
AdverseDrive
Attacking Vision based Perception in End-to-end Autonomous Driving Models
Stars: ✭ 24 (-48.94%)
Mutual labels:  carla-simulator
dig-into-apollo
Apollo notes (Apollo学习笔记) - Apollo learning notes for beginners.
Stars: ✭ 1,786 (+3700%)
Mutual labels:  autonomous-driving
YOLOP
You Only Look Once for Panopitic Driving Perception.(https://arxiv.org/abs/2108.11250)
Stars: ✭ 1,228 (+2512.77%)
Mutual labels:  autonomous-driving
bark-ml
Gym environments and agents for autonomous driving.
Stars: ✭ 68 (+44.68%)
Mutual labels:  autonomous-driving
LiDAR fog sim
LiDAR fog simulation
Stars: ✭ 101 (+114.89%)
Mutual labels:  autonomous-driving
SelfDrivingRCCar
Autonomous RC Car using Neural Networks, Python and Open CV
Stars: ✭ 102 (+117.02%)
Mutual labels:  autonomous-driving
anomaly-seg
The Combined Anomalous Object Segmentation (CAOS) Benchmark
Stars: ✭ 115 (+144.68%)
Mutual labels:  carla-simulator
carla-rl
Reinforcement Learning Agents Trained in the CARLA Simulator
Stars: ✭ 77 (+63.83%)
Mutual labels:  carla-simulator

Carla Data Export

This repository contains the code we used for generating training data from the CARLA simulator in our paper Multimodal 3D Object Detection from Simulated Pretraining

Installation

Download and extract CARLA 0.8.4 from https://github.com/carla-simulator/carla/releases/tag/0.8.4
This project expects the carla folder to be inside this project i.e PythonClient/carla-data-export/carla
Install all the necessary requirements for your python environment using:

pip install -r requirements.txt

⚠️ Note: The project has only been tested with Python 3.x <= 3.6

Generating data

Before the data generation scripts can be run you must start a CARLA server. This can be done by running the executable in the CARLA root folder with the appropriate parameters. Running the server on windows in a small 200x200 window would for example be:

./CarlaUE4.exe -carla-server -fps=10 -windowed -ResX=200 -ResY=200

Once the server is running, data generation can be started using (remove --autopilot for manual control):

python datageneration.py --autopilot

Citation

If you have used our work, please cite our paper:

@article{brekke2019multimodal,
  title={Multimodal 3D Object Detection from Simulated Pretraining},
  author={Brekke, {\AA}smund and Vatsendvik, Fredrik and Lindseth, Frank},
  journal={arXiv preprint arXiv:1905.07754},
  year={2019}
}
Note that the project description data, including the texts, logos, images, and/or trademarks, for each open source project belongs to its rightful owner. If you wish to add or remove any projects, please contact us at [email protected].