All Projects → hellojialee → Traffic_sign_recognition_efficient_cnns

hellojialee / Traffic_sign_recognition_efficient_cnns

Licence: mit
A repository for the paper "Real-Time Traffic Sign Recognition Based on Efficient CNNs in the Wild"

Programming Languages

python
139335 projects - #7 most used programming language

Projects that are alternatives of or similar to Traffic sign recognition efficient cnns

Maps Location History
Get, Concatenate and Process you location history from Google Maps TimeLine
Stars: ✭ 99 (-1.98%)
Mutual labels:  jupyter-notebook
Unet
Generic U-Net Tensorflow 2 implementation for semantic segmentation
Stars: ✭ 100 (-0.99%)
Mutual labels:  jupyter-notebook
Genetic Algorithm
Genetic algorithm tutorial for Python
Stars: ✭ 101 (+0%)
Mutual labels:  jupyter-notebook
Awesome Pytorch List Cnversion
Awesome-pytorch-list 翻译工作进行中......
Stars: ✭ 1,361 (+1247.52%)
Mutual labels:  jupyter-notebook
Sequana
Sequana: a set of Snakemake NGS pipelines
Stars: ✭ 100 (-0.99%)
Mutual labels:  jupyter-notebook
Airbnb Amenity Detection
Repo for 42 days project to replicate/improve Airbnb's amenity (object) detection pipeline.
Stars: ✭ 101 (+0%)
Mutual labels:  jupyter-notebook
Mxnet Finetuner
An all-in-one Deep Learning toolkit for image classification to fine-tuning pretrained models using MXNet.
Stars: ✭ 100 (-0.99%)
Mutual labels:  jupyter-notebook
Data Driven Discretization 1d
Code for "Learning data-driven discretizations for partial differential equations"
Stars: ✭ 101 (+0%)
Mutual labels:  jupyter-notebook
Noworkflow
Supporting infrastructure to run scientific experiments without a scientific workflow management system.
Stars: ✭ 100 (-0.99%)
Mutual labels:  jupyter-notebook
Context aug
Context-driven data augmentation for Object Detection (ECCV'18)
Stars: ✭ 101 (+0%)
Mutual labels:  jupyter-notebook
Europilot
A toolkit for controlling Euro Truck Simulator 2 with python to develop self-driving algorithms.
Stars: ✭ 1,366 (+1252.48%)
Mutual labels:  jupyter-notebook
Dadoware
Brazilian-Portuguese word list and instructions booklet for Diceware
Stars: ✭ 100 (-0.99%)
Mutual labels:  jupyter-notebook
Mish Cuda
Mish Activation Function for PyTorch
Stars: ✭ 101 (+0%)
Mutual labels:  jupyter-notebook
Text Classification
An example on how to train supervised classifiers for multi-label text classification using sklearn pipelines
Stars: ✭ 100 (-0.99%)
Mutual labels:  jupyter-notebook
Spectralnormalizationkeras
Spectral Normalization for Keras Dense and Convolution Layers
Stars: ✭ 100 (-0.99%)
Mutual labels:  jupyter-notebook
Data What Now
All codes from the DataWhatNow blog.
Stars: ✭ 100 (-0.99%)
Mutual labels:  jupyter-notebook
Codeinquarantine
Stars: ✭ 101 (+0%)
Mutual labels:  jupyter-notebook
Nn From Scratch
Implementing a Neural Network from Scratch
Stars: ✭ 1,374 (+1260.4%)
Mutual labels:  jupyter-notebook
Cvnd localization exercises
Notebooks for learning about object motion and localization methods in the last section of CVND.
Stars: ✭ 101 (+0%)
Mutual labels:  jupyter-notebook
Hass Deepstack Face
Home Assistant custom component for using Deepstack face recognition
Stars: ✭ 101 (+0%)
Mutual labels:  jupyter-notebook

Traffic_Sign_Recognition_Efficient_CNNs

A repository for the paper "Real-Time Traffic Sign Recognition Based on Efficient CNNs in the Wild" https://ieeexplore.ieee.org/document/8392744/

Efficient CNNs for traffic sign recognition

Project Include:

Traffic sign detector

Traffic sign classifer

Localization refinment

We show our work as three separate steps which are not difficult to be integrated into a complete pipeline.

image

image

image

Citation

Please cite the paper in your publications if it helps your research:

@article{li2018real,
  title={Real-time traffic sign recognition based on efficient CNNs in the wild},
  author={Li, Jia and Wang, Zengfu},
  journal={IEEE Transactions on Intelligent Transportation Systems},
  volume={20},
  number={3},
  pages={975--984},
  year={2018},
  publisher={IEEE}
}
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].