Key Points Estimation and Point Instance Segmentation Approach for Lane Detection

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 https://github.com/koyeongmin/PINet_new

arXiv commentSubmitted to "IEEE Transactions on Intelligent Transportation Systems"

References in corpus (6)

• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
• ENet: A Deep Neural Network Architecture for Real-Time Semantic Segmentation
• Semantic Instance Segmentation with a Discriminative Loss Function
• Spatial As Deep: Spatial CNN for Traffic Scene Understanding
• Rethinking on Multi-Stage Networks for Human Pose Estimation

Cited by in corpus (12)

• Lane Detection Model Based on Spatio-Temporal Network With Double Convolutional Gated Recurrent Units
• A Hybrid Spatial-temporal Deep Learning Architecture for Lane Detection
• RESA: Recurrent Feature-Shift Aggregator for Lane Detection
• Dirty Road Can Attack: Security of Deep Learning based Automated Lane Centering under Physical-World Attack
• CondLaneNet: a Top-to-down Lane Detection Framework Based on Conditional Convolution
• Focus on Local: Detecting Lane Marker from Bottom Up via Key Point
• End-to-end Lane Shape Prediction with Transformers
• Flexible 3D Lane Detection by Hierarchical Shape MatchingFlexible 3D Lane Detection by Hierarchical Shape Matching
• Structure Guided Lane Detection
• Lane detection in complex scenes based on end-to-end neural network
• Model-Agnostic Defense for Lane Detection against Adversarial Attack
• Hybrid tracker based optimal path tracking system for complex road environments for autonomous driving