Leveraging Road Area Semantic Segmentation with Auxiliary Steering Task

TL;DR

This paper introduces a CNN-based approach that uses auxiliary steering angle data to enhance road area semantic segmentation, reducing the need for manual annotation in diverse driving conditions.

Contribution

The method leverages easily obtainable steering data to improve segmentation accuracy without manual annotation, demonstrating effectiveness across challenging datasets.

Findings

0.1-2.9% improvement in mIoU over transfer learning models

Effective in diverse adverse weather and road conditions

Utilizes auxiliary steering task to boost segmentation performance

Abstract

Robustness of different pattern recognition methods is one of the key challenges in autonomous driving, especially when driving in the high variety of road environments and weather conditions, such as gravel roads and snowfall. Although one can collect data from these adverse conditions using cars equipped with sensors, it is quite tedious to annotate the data for training. In this work, we address this limitation and propose a CNN-based method that can leverage the steering wheel angle information to improve the road area semantic segmentation. As the steering wheel angle data can be easily acquired with the associated images, one could improve the accuracy of road area semantic segmentation by collecting data in new road environments without manual data annotation. We demonstrate the effectiveness of the proposed approach on two challenging data sets for autonomous driving and show that when the steering task is used in our segmentation model training, it leads to a 0.1-2.9% gain in the road area mIoU (mean Intersection over Union) compared to the corresponding reference transfer learning model.