Key Points Estimation and Point Instance Segmentation Approach for Lane Detection (2020-02-16T00:00:00.000000Z)

TL;DR

A traffic line detection method called Point Instance Network (PINet), based on the key points estimation and instance segmentation approach, which achieves competitive accuracy and false positive on the TuSimple and Culane datasets.

Abstract

Perception techniques for autonomous driving should be adaptive to various environments. In the case of traffic line detection, an essential perception module, many condition should be considered, such as number of traffic lines and computing power of the target system. To address these problems, in this paper, we propose a traffic line detection method called Point Instance Network (PINet); the method is based on the key points estimation and instance segmentation approach. The PINet includes several stacked hourglass networks that are trained simultaneously. Therefore the size of the trained models can be chosen according to the computing power of the target environment. We cast a clustering problem of the predicted key points as an instance segmentation problem; the PINet can be trained regardless of the number of the traffic lines. The PINet achieves competitive accuracy and false positive on the TuSimple and Culane datasets, popular public datasets for lane detection. Our code is available at this https URL

Authors

M. Jeon

5 papers

Jiwon Jun

2 papers

Yeongmin Ko

1 papers

TL;DR

Abstract

Authors

References53 items

Multiple Lane Detection via Combining Complementary Structural Constraints

ADFNet: accumulated decoder features for real-time semantic segmentation

Line-CNN: End-to-End Traffic Line Detection With Line Proposal Unit

Where Am I: Localization and 3D Maps for Autonomous Vehicles

SNIDER: Single Noisy Image Denoising and Rectification for Improving License Plate Recognition

Learning Lightweight Lane Detection CNNs by Self Attention Distillation

Self-Supervised Drivable Area and Road Anomaly Segmentation Using RGB-D Data For Robotic Wheelchairs

Multi-Class Lane Semantic Segmentation using Efficient Convolutional Networks

PointLaneNet: Efficient end-to-end CNNs for Accurate Real-Time Lane Detection

CenterNet: Keypoint Triplets for Object Detection

A Novel Strategy for Road Lane Detection and Tracking Based on a Vehicle’s Forward Monocular Camera

Robust Lane Detection From Continuous Driving Scenes Using Deep Neural Networks

End-to-end Lane Detection through Differentiable Least-Squares Fitting

Bottom-Up Object Detection by Grouping Extreme and Center Points

Rethinking on Multi-Stage Networks for Human Pose Estimation

PoseFix: Model-Agnostic General Human Pose Refinement Network

EL-GAN: Embedding Loss Driven Generative Adversarial Networks for Lane Detection

2018 IEEE Intelligent Vehicles Symposium (IV)

Robust Lane Detection and Tracking for Real-Time Applications

Towards End-to-End Lane Detection: an Instance Segmentation Approach

Spatial As Deep: Spatial CNN for Traffic Scene Understanding

SGPN: Similarity Group Proposal Network for 3D Point Cloud Instance Segmentation

Semantic Instance Segmentation with a Discriminative Loss Function

Learning Feature Pyramids for Human Pose Estimation

Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks

Mask R-CNN

Paying More Attention to Attention: Improving the Performance of Convolutional Neural Networks via Attention Transfer

Road detection algorithm for Autonomous Navigation Systems based on dark channel prior and vanishing point in complex road scenes

ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation

Stacked Hourglass Networks for Human Pose Estimation

SegNet: A Deep Convolutional Encoder-Decoder Architecture for Image Segmentation

You Only Look Once: Unified, Real-Time Object Detection

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

U-Net: Convolutional Networks for Biomedical Image Segmentation

Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift

Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification

Generative Adversarial Nets

Combining Priors, Appearance, and Context for Road Detection

ImageNet classification with deep convolutional neural networks

A random finite set approach to multiple lane detection

A Novel Lane Detection System With Efficient Ground Truth Generation

Robust lane detection and tracking with ransac and Kalman filter

Robust Lane Detection and Tracking in Challenging Scenarios

Lane detection using color-based segmentation

Color-based road detection in urban traffic scenes

Lane detection and tracking using B-Snake

Three-feature based automatic lane detection algorithm (TFALDA) for autonomous driving

Use of the Hough transformation to detect lines and curves in pictures

Improved Lane Detection With Multilevel Features in Branch Convolutional Neural Networks

”Centernet: Object detection with keypoint triplets.”

, et al . ” Spatial as deep : Spatial cnn for traffic scene understanding . ” Thirty - Second AAAI Conference on Artificial Intelligence .

LANE DETECTION USING CATMULL-ROM SPLINE

The TuSimple lane challenge

Field of Study

Journal Information

Name

Volume

Venue Information

Name

Type

URL

Alternate Names