LIDAR-Camera Fusion for Road Detection Using Fully Convolutional Neural Networks

By Luca Caltagirone, Mauro Bellone, Lennart Svensson, Mattias Wahde. Robotics Auton. Syst., 2018

345 citations recorded by the source corpus.

Abstract In this work, a deep learning approach has been developed to carry out road detection by fusing LIDAR point clouds and camera images. An unstructured and sparse point cloud is first projected onto the camera image plane and then upsampled to obtain a set of dense 2D images encoding spatial information. Several fully convolutional neural networks (FCNs) are then trained to carry out road detection, either by using data from a single sensor, or by using three fusion strategies: early, late, and the newly proposed cross fusion. Whereas in the former two fusion approaches, the integration of multimodal information is carried out at a predefined depth level, the cross fusion FCN is designed to directly learn from data where to integrate information; this is accomplished by using trainable cross connections between the LIDAR and the camera processing branches. To further highlight the benefits of using a multimodal system for road detection, a data set consisting of visually challenging scenes was extracted from driving sequences of the KITTI raw data set. It was then demonstrated that, as expected, a purely camera-based FCN severely underperforms on this data set. A multimodal system, on the other hand, is still able to provide high accuracy. Finally, the proposed cross fusion FCN was evaluated on the KITTI road benchmark where it achieved excellent performance, with a MaxF score of 96.03%, ranking it among the top-performing approaches.

Subfields: Automotive Engineering, Computer Vision and Pattern Recognition, Environmental Engineering

View Paper: https://www.semanticscholar.org/paper/4c60815ea05ff4b9f7301b28b8dd6017d64877bd

How researchers see this paper

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

In Automotive Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Multi-Sensor Fusion in Automated Driving: A Survey (2020, methodology): “It is worth mentioning that in reference [88], the data of the LiDAR and the camera are carried out by using the fully convolutional neural network (FCN).”
A Deep Learning-based Radar and Camera Sensor Fusion Architecture for Object Detection (2019, methodology): “A similar technique has been applied by [16].”
State of the Art of Automated Buses (2018, methodology): “12 reports some example of road detection using different artificial intelligence methods and different data sources, in (a) 3D data from a stereo camera are used [39], whereas in (b) a fusion between camera images and LIDAR data was presented [40].”