A Sensor-Fusion Drivable-Region and Lane-Detection System for Autonomous Vehicle Navigation in Challenging Road Scenarios

By Qingquan Li, Long Chen, Ming Li, Shih-Lung Shaw, Andreas Nüchter. 2014

348 citations recorded by the source corpus.

Autonomous vehicle navigation is challenging since various types of road scenarios in real urban environments have to be considered, particularly when only perception sensors are used, without position information. This paper presents a novel real-time optimal-drivable-region and lane detection system for autonomous driving based on the fusion of light detection and ranging (LIDAR) and vision data. Our system uses a multisensory scheme to cover the most drivable areas in front of a vehicle. We propose a feature-level fusion method for the LIDAR and vision data and an optimal selection strategy for detecting the best drivable region. Then, a conditional lane detection algorithm is selectively executed depending on the automatic classification of the optimal drivable region. Our system successfully handles both structured and unstructured roads. The results of several experiments are provided to demonstrate the reliability, effectiveness, and robustness of the system.

Subfields: Aerospace Engineering, Automotive Engineering, Plant Science

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

1. Chunhong Pan
2. Chau Yuen
3. Shiming Xiang
4. Long Chen
5. Yunyi Yang
6. Ying Wang
7. Shibiao Xu
8. Hongzhen Wang

In Automotive Engineering

1. Qin Zou
2. Chunhong Pan
3. Chau Yuen
4. Shiming Xiang
5. Long Chen
6. Qiyu Dai
7. Hanwen Jiang
8. Qian Wang

Citations in the corpus

• A survey of data fusion in smart city applications (2019, methodology): “As for the autonomous vehicle system, the control of an autonomous vehicle itself is a complex data fusion process, fusing various data sources about the vehicle and the road by advanced machine learning and control algorithms [140], [206].”
• Robust Lane Detection From Continuous Driving Scenes Using Deep Neural Networks (2019, background): “In the past two decades, a number of researches have been made in the fields of lane detection and prediction [24]–[27].”
• DSNet: Joint Learning for Scene Segmentation and Disparity Estimation (2019, background): “Another efficient research is from perception system [21], such as [9] which transforms a 3D lidar point cloud into a 2-”
• Automatic Road Detection and Centerline Extraction via Cascaded End-to-End Convolutional Neural Network (2017, background): “It is an essential preprocessing step for various applications, such as vehicle navigation [1], urban planning, image registration, geographic information system update [2], and so on.”