# Embedding Structured Contour and Location Prior in Siamesed Fully Convolutional Networks for Road Detection

## TL;DR

This paper introduces s-FCN-loc, a deep learning model that integrates RGB images, semantic contours, and location priors to improve road detection accuracy and training speed in autonomous driving.

## Contribution

The paper proposes a novel s-FCN-loc model that combines multiple features and location priors for more accurate and faster road detection compared to existing FCN methods.

## Key findings

- s-FCN-loc detects more accurate road boundaries.
- Training speed is 30% faster than original FCN.
- Achieves competitive results on KITTI and other datasets.

## Abstract

Road detection from the perspective of moving vehicles is a challenging issue in autonomous driving. Recently, many deep learning methods spring up for this task because they can extract high-level local features to find road regions from raw RGB data, such as Convolutional Neural Networks (CNN) and Fully Convolutional Networks (FCN). However, how to detect the boundary of road accurately is still an intractable problem. In this paper, we propose a siamesed fully convolutional networks (named as ``s-FCN-loc''), which is able to consider RGB-channel images, semantic contours and location priors simultaneously to segment road region elaborately. To be specific, the s-FCN-loc has two streams to process the original RGB images and contour maps respectively. At the same time, the location prior is directly appended to the siamesed FCN to promote the final detection performance. Our contributions are threefold: (1) An s-FCN-loc is proposed that learns more discriminative features of road boundaries than the original FCN to detect more accurate road regions; (2) Location prior is viewed as a type of feature map and directly appended to the final feature map in s-FCN-loc to promote the detection performance effectively, which is easier than other traditional methods, namely different priors for different inputs (image patches); (3) The convergent speed of training s-FCN-loc model is 30\% faster than the original FCN, because of the guidance of highly structured contours. The proposed approach is evaluated on KITTI Road Detection Benchmark and One-Class Road Detection Dataset, and achieves a competitive result with state of the arts.