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

A. Hernandez, S. Woo, H. Corrales, I. Parra, E. Kim, D. F. Llorca, M. A. Sotelo

Research output: Contribution to conferencePaperpeer-review

2 Citations (Scopus)


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 is 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 KITTI dataset the model has achieved an F1 error value of 97.85% in validation and 96.02% using the test images.

Original languageEnglish
Number of pages7
Publication statusPublished - 2020
Event31st IEEE Intelligent Vehicles Symposium, IV 2020 - Virtual, Las Vegas, United States
Duration: 2020 Oct 192020 Nov 13


Conference31st IEEE Intelligent Vehicles Symposium, IV 2020
Country/TerritoryUnited States
CityVirtual, Las Vegas

Bibliographical note

Funding Information:
This work was supported in part by Spanish Ministry of Science, Innovation and Universities (Research Grant DPI2017-90035-R) and in part by the Community Region of Madrid (Research Grant 2018/EMT-4362 SEGVAUTO 4.0-CM) and BRAVE Project, H2020, Contract #723021. This project has received funding from the Electronic Component Systems for European Leadership Joint Undertaking under grant agreement No 737469 (AutoDrive Project) and in part by the Spanish Ministry of Economy (Research Grant PCIN-2017-086). This Joint Undertaking receives support from the European Unions Horizon 2020 research and innovation programme and Germany, Austria, Spain, Italy, Latvia, Belgium, Netherlands, Sweden, Finland, Lithuania, Czech Republic, Romania, Norway. We gratefully acknowledge the support of NVIDIA Corporation with the donation of the GPUs used for this Research.

Publisher Copyright:
© 2020 IEEE.

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Automotive Engineering
  • Modelling and Simulation


Dive into the research topics of '3D-DEEP: 3-Dimensional Deep-learning based on elevation patterns for road scene interpretation'. Together they form a unique fingerprint.

Cite this