3D-DEEP: 3-Dimensional Deep-learning based on elevation patterns forroad scene interpretation

TL;DR

This paper introduces 3D-DEEP, a novel 3D deep learning architecture utilizing elevation patterns from disparity and LiDAR data for improved road scene interpretation in autonomous driving.

Contribution

The paper presents a new CNN architecture, 3D-DEEP, that effectively integrates 3D information from disparity and LiDAR for semantic segmentation of road scenes.

Findings

Achieved 72.32% mIoU on Cityscapes dataset.

Obtained 97.85% F1 error on KITTI validation set.

Achieved 96.02% F1 score on KITTI test set.

Abstract

Road detection and segmentation is a crucial task in computer vision for safe autonomous driving. With this in mind, a new net architecture (3D-DEEP) and its end-to-end training methodology for CNN-based semantic segmentation are described along this paper for. The method relies on disparity filtered and LiDAR projected images for three-dimensional information and image feature extraction through fully convolutional networks architectures. The developed models were trained and validated over Cityscapes dataset using just fine annotation examples with 19 different training classes, and over KITTI road dataset. 72.32% mean intersection over union(mIoU) has been obtained for the 19 Cityscapes training classes using the validation images. On the other hand, over KITTIdataset the model has achieved an F1 error value of 97.85% invalidation and 96.02% using the test images.