This repository holds the source code for Temporal-LaneATT, a lane detectiom model proposed in the IJCNN'22 paper "Lane Marking Detection and Classification using Spatial-Temporal Feature Pooling", by Lucas Tabelini, Rodrigo Berriel, Alberto F. De Souza, Claudine Badue, and Thiago Oliveira-Santos.
The processes for installation and usage are the same ones used for LaneATT. Please follow the instructions on the project's page.
Pre-trained models can be found here.
If you use this code in your research, please cite:
@InProceedings{tabelini2022ijcnn,
author = {Lucas Tabelini
and Rodrigo Berriel
and Alberto Ferreira De Souza
and Claudine Badue
and Thiago Oliveira-Santos},
title = {{Lane Marking Detection and Classification using Spatial-Temporal Feature Pooling}},
booktitle = {International Joint Conference on Neural Networks (IJCNN)},
year = {2022}
}