PyTorch implementation of 'Gen-LaneNet: a generalized and scalable approach for 3D lane detection'

Overview

(pytorch) Gen-LaneNet: a generalized and scalable approach for 3D lane detection

Introduction

This is a pytorch implementation of Gen-LaneNet, which predicts 3D lanes from a single image. Specifically, Gen-LaneNet is a unified network solution that solves image encoding, spatial transform of features and 3D lane prediction simultaneously. The method refers to the ECCV 2020 paper:

'Gen-LaneNet: a generalized and scalable approach for 3D lane detection', Y Guo, etal. ECCV 2020. [eccv][arxiv]

Key features:

  • A geometry-guided lane anchor representation generalizable to novel scenes.

  • A scalable two-stage framework that decouples the learning of image segmentation subnetwork and geometry encoding subnetwork.

  • A synthetic dataset for 3D lane detection [repo] [data].

Another baseline

This repo also includes an unofficial implementation of '3D-LaneNet' in pytorch for comparison. The method refers to

"3d-lanenet: end-to-end 3d multiple lane detection", N. Garnet, etal., ICCV 2019. [paper]

Requirements

If you have Anaconda installed, you can directly import the provided environment file.

conda env update --file environment.yaml

Those important packages includes:

  • opencv-python 4.1.0.25
  • pytorch 1.4.0
  • torchvision 0.5.0
  • tensorboard 1.15.0
  • tensorboardx 1.7
  • py3-ortools 5.1.4041

Data preparation

The 3D lane detection method is trained and tested on the 3D lane synthetic dataset. Running the demo code on a single image should directly work. However, repeating the training, testing and evaluation requires to prepare the dataset:

If you prefer to build your own data splits using the dataset, please follow the steps described in the 3D lane synthetic dataset repository. All necessary codes are included here already.

Run the Demo

python main_demo_GenLaneNet_ext.py

Specifically, this code predict 3D lane from an image given known camera height and pitch angle. Pretrained models for the segmentation subnetwork and the 3D geometry subnetwork are loaded. Meanwhile, anchor normalization parameters wrt. the training set are also loaded. The demo code will produce lane predication from a single image visualized in the following figure.

The lane results are visualized in three coordinate frames, respectively image plane, virtual top-view, and ego-vehicle coordinate frame. The lane-lines are shown in the top row and the center-lines are shown in the bottom row.

How to train the model

Step 1: Train the segmentation subnetwork

The training of Gen-LaneNet requires to first train the segmentation subnetwork, ERFNet.

  • The training of the ERFNet is based on a pytorch implementation [repo] modified to train the model on the 3D lane synthetic dataset.

  • The trained model should be saved as 'pretrained/erfnet_model_sim3d.tar'. A pre-trained model is already included.

Step 2: Train the 3D-geometry subnetwork

python main_train_GenLaneNet_ext.py
  • Set 'args.dataset_name' to a certain data split to train the model.
  • Set 'args.dataset_dir' to the folder saving the raw dataset.
  • The trained model will be saved in the directory corresponding to certain data split and model name, e.g. 'data_splits/illus_chg/Gen_LaneNet_ext/model*'.
  • The anchor offset std will be recorded for certain data split at the same time, e.g. 'data_splits/illus_chg/geo_anchor_std.json'.

The training progress can be monitored by tensorboard as follows.

cd datas_splits/Gen_LaneNet_ext
./tensorboard  --logdir ./

Batch testing

python main_test_GenLaneNet_ext.py
  • Set 'args.dataset_name' to a certain data split to test the model.
  • Set 'args.dataset_dir' to the folder saving the raw dataset.

The batch testing code not only produces the prediction results, e.g., 'data_splits/illus_chg/Gen_LaneNet_ext/test_pred_file.json', but also perform full-range precision-recall evaluation to produce AP and max F-score.

Other methods

In './experiments', we include the training codes for other variants of Gen-LaneNet models as well as for the baseline method 3D-LaneNet as well as its extended version integrated with the new anchor proposed in Gen-LaneNet. Interested users are welcome to repeat the full set of ablation study reported in the gen-lanenet paper. For example, to train 3D-LaneNet:

cd experiments
python main_train_3DLaneNet.py

Evaluation

Stand-alone evaluation can also be performed.

cd tools
python eval_3D_lane.py

Basically, you need to set 'method_name' and 'data_split' properly to compare the predicted lanes against ground-truth lanes. Evaluation details can refer to the 3D lane synthetic dataset repository or the Gen-LaneNet paper. Overall, the evaluation metrics include:

  • Average Precision (AP)
  • max F-score
  • x-error in close range (0-40 m)
  • x-error in far range (40-100 m)
  • z-error in close range (0-40 m)
  • z-error in far range (40-100 m)

We show the evaluation results comparing two methods:

  • "3d-lanenet: end-to-end 3d multiple lane detection", N. Garnet, etal., ICCV 2019
  • "Gen-lanenet: a generalized and scalable approach for 3D lane detection", Y. Guo, etal., Arxiv, 2020 (GenLaneNet_ext in code)

Comparisons are conducted under three distinguished splits of the dataset. For simplicity, only lane-line results are reported here. The results from the code could be marginally different from that reported in the paper due to different random splits.

  • Standard
Method AP F-Score x error near (m) x error far (m) z error near (m) z error far (m)
3D-LaneNet 89.3 86.4 0.068 0.477 0.015 0.202
Gen-LaneNet 90.1 88.1 0.061 0.496 0.012 0.214
  • Rare Subset
Method AP F-Score x error near (m) x error far (m) z error near (m) z error far (m)
3D-LaneNet 74.6 72.0 0.166 0.855 0.039 0.521
Gen-LaneNet 79.0 78.0 0.139 0.903 0.030 0.539
  • Illumination Change
Method AP F-Score x error near (m) x error far (m) z error near (m) z error far (m)
3D-LaneNet 74.9 72.5 0.115 0.601 0.032 0.230
Gen-LaneNet 87.2 85.3 0.074 0.538 0.015 0.232

Visualization

Visual comparisons to the ground truth can be generated per image when setting 'vis = True' in 'tools/eval_3D_lane.py'. We show two examples for each method under the data split involving illumination change.

  • 3D-LaneNet

  • Gen-LaneNet

Citation

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

@article{guo2020gen,
  title={Gen-LaneNet: A Generalized and Scalable Approach for 3D Lane Detection},
  author={Yuliang Guo, Guang Chen, Peitao Zhao, Weide Zhang, Jinghao Miao, Jingao Wang, and Tae Eun Choe},
  booktitle={Computer Vision - {ECCV} 2020 - 16th European Conference},
  year={2020}
}

Copyright and License

The copyright of this work belongs to Baidu Apollo, which is provided under the Apache-2.0 license.

Owner
Yuliang Guo
Researcher in Computer Vision
Yuliang Guo
Implementation of Bidirectional Recurrent Independent Mechanisms (Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neural Networks with Attention over Modules)

BRIMs Bidirectional Recurrent Independent Mechanisms Implementation of the paper Learning to Combine Top-Down and Bottom-Up Signals in Recurrent Neura

Sarthak Mittal 26 May 26, 2022
The source code and dataset for the RecGURU paper (WSDM 2022)

RecGURU About The Project Source code and baselines for the RecGURU paper "RecGURU: Adversarial Learning of Generalized User Representations for Cross

Chenglin Li 17 Jan 07, 2023
DGL-TreeSearch and the Gurobi-MWIS interface

Independent Set Benchmarking Suite This repository contains the code for our maximum independent set benchmarking suite as well as our implementations

Maximilian Böther 19 Nov 22, 2022
Rule Extraction Methods for Interactive eXplainability

REMIX: Rule Extraction Methods for Interactive eXplainability This repository contains a variety of tools and methods for extracting interpretable rul

Mateo Espinosa Zarlenga 21 Jan 03, 2023
This folder contains the python code of UR5E's advanced forward kinematics model.

This folder contains the python code of UR5E's advanced forward kinematics model. By entering the angle of the joint of UR5e, the detailed coordinates of up to 48 points around the robot arm can be c

Qiang Wang 4 Sep 17, 2022
Towards Interpretable Deep Metric Learning with Structural Matching

DIML Created by Wenliang Zhao*, Yongming Rao*, Ziyi Wang, Jiwen Lu, Jie Zhou This repository contains PyTorch implementation for paper Towards Interpr

Wenliang Zhao 75 Nov 11, 2022
GRaNDPapA: Generator of Rad Names from Decent Paper Acronyms

GRaNDPapA: Generator of Rad Names from Decent Paper Acronyms Trying to publish a new machine learning model and can't write a decent title for your pa

264 Nov 08, 2022
Pytorch implementation of our paper accepted by NeurIPS 2021 -- Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme

Revisiting Discriminator in GAN Compression: A Generator-discriminator Cooperative Compression Scheme (NeurIPS2021) (Link) Overview Prerequisites Linu

Shaojie Li 34 Mar 31, 2022
FridaHookAppTool - Frida Hook App Tool With Python

FridaHookAppTool(以下是Hook mpaas框架的例子) mpaas移动开发框架ios端抓包hook脚本 使用方法:链接数据线,开启burp设置

13 Nov 30, 2022
Official Code for ICML 2021 paper "Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline"

Revisiting Point Cloud Shape Classification with a Simple and Effective Baseline Ankit Goyal, Hei Law, Bowei Liu, Alejandro Newell, Jia Deng Internati

Princeton Vision & Learning Lab 115 Jan 04, 2023
Code artifacts for the submission "Mind the Gap! A Study on the Transferability of Virtual vs Physical-world Testing of Autonomous Driving Systems"

Code Artifacts Code artifacts for the submission "Mind the Gap! A Study on the Transferability of Virtual vs Physical-world Testing of Autonomous Driv

Andrea Stocco 2 Aug 24, 2022
Python scripts to detect faces in Python with the BlazeFace Tensorflow Lite models

Python scripts to detect faces using Python with the BlazeFace Tensorflow Lite models. Tested on Windows 10, Tensorflow 2.4.0 (Python 3.8).

Ibai Gorordo 46 Nov 17, 2022
Kaggle | 9th place single model solution for TGS Salt Identification Challenge

UNet for segmenting salt deposits from seismic images with PyTorch. General We, tugstugi and xuyuan, have participated in the Kaggle competition TGS S

Erdene-Ochir Tuguldur 276 Dec 20, 2022
ICLR 2021 i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning

Introduction PyTorch code for the ICLR 2021 paper [i-Mix: A Domain-Agnostic Strategy for Contrastive Representation Learning]. @inproceedings{lee2021i

Kibok Lee 68 Nov 27, 2022
Code repository for "Reducing Underflow in Mixed Precision Training by Gradient Scaling" presented at IJCAI '20

Reducing Underflow in Mixed Precision Training by Gradient Scaling This project implements the gradient scaling method to improve the performance of m

Ruizhe Zhao 5 Apr 14, 2022
[CVPR2021] UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicles

UAV-Human Official repository for CVPR2021: UAV-Human: A Large Benchmark for Human Behavior Understanding with Unmanned Aerial Vehicle Paper arXiv Res

129 Jan 04, 2023
Implementation of DropLoss for Long-Tail Instance Segmentation in Pytorch

[AAAI 2021]DropLoss for Long-Tail Instance Segmentation [AAAI 2021] DropLoss for Long-Tail Instance Segmentation Ting-I Hsieh*, Esther Robb*, Hwann-Tz

Tim 37 Dec 02, 2022
Code for "Discovering Non-monotonic Autoregressive Orderings with Variational Inference" (paper and code updated from ICLR 2021)

Discovering Non-monotonic Autoregressive Orderings with Variational Inference Description This package contains the source code implementation of the

Xuanlin (Simon) Li 10 Dec 29, 2022
Matthew Colbrook 1 Apr 08, 2022
minimizer-space de Bruijn graphs (mdBG) for whole genome assembly

rust-mdbg: Minimizer-space de Bruijn graphs (mdBG) for whole-genome assembly rust-mdbg is an ultra-fast minimizer-space de Bruijn graph (mdBG) impleme

Barış Ekim 148 Dec 01, 2022