DeepAI AI Chat
Log In Sign Up

Contextual road lane and symbol generation for autonomous driving

by   Ajay Soni, et al.
ZF Friedrichshafen

In this paper we present a novel approach for lane detection and segmentation using generative models. Traditionally discriminative models have been employed to classify pixels semantically on a road. We model the probability distribution of lanes and road symbols by training a generative adversarial network. Based on the learned probability distribution, context-aware lanes and road signs are generated for a given image which are further quantized for nearest class label. Proposed method has been tested on BDD100K and Baidu ApolloScape datasets and performs better than state of the art and exhibits robustness to adverse conditions by generating lanes in faded out and occluded scenarios.


page 3

page 7

page 8


Agnostic Lane Detection

Lane detection is an important yet challenging task in autonomous drivin...

A Methodological Review of Visual Road Recognition Procedures for Autonomous Driving Applications

The current research interest in autonomous driving is growing at a rapi...

Regularized Generative Adversarial Network

We propose a framework for generating samples from a probability distrib...

Map-Enhanced Ego-Lane Detection in the Missing Feature Scenarios

As one of the most important tasks in autonomous driving systems, ego-la...

Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car

As part of a complete software stack for autonomous driving, NVIDIA has ...

VPGNet: Vanishing Point Guided Network for Lane and Road Marking Detection and Recognition

In this paper, we propose a unified end-to-end trainable multi-task netw...

Memory Guided Road Detection

In self driving car applications, there is a requirement to predict the ...