# Lane Detection and Classification using Cascaded CNNs

## TL;DR

This paper introduces a real-time, end-to-end system using cascaded CNNs for lane boundary detection, classification, and clustering, enhancing autonomous vehicle navigation with detailed lane information.

## Contribution

The work presents a novel cascaded CNN architecture for simultaneous lane boundary detection and classification, trained on a new labeled dataset with eight lane classes.

## Key findings

- Achieved real-time performance in lane detection and classification
- Labeled 14,336 lane boundary instances with 8 classes for training
- System improves lane understanding for autonomous driving applications

## Abstract

Lane detection is extremely important for autonomous vehicles. For this reason, many approaches use lane boundary information to locate the vehicle inside the street, or to integrate GPS-based localization. As many other computer vision based tasks, convolutional neural networks (CNNs) represent the state-of-the-art technology to indentify lane boundaries. However, the position of the lane boundaries w.r.t. the vehicle may not suffice for a reliable positioning, as for path planning or localization information regarding lane types may also be needed. In this work, we present an end-to-end system for lane boundary identification, clustering and classification, based on two cascaded neural networks, that runs in real-time. To build the system, 14336 lane boundaries instances of the TuSimple dataset for lane detection have been labelled using 8 different classes. Our dataset and the code for inference are available online.