We present a deep convolutional neural network (CNN) architecture for high-precision depth estimation by jointly utilizing sparse 3D LiDAR and dense stereo depth information. In this network, the complementary characteristics of sparse 3D LiDAR and dense stereo depth are simultaneously encoded in a boosting manner. Tailored to the LiDAR and stereo fusion problem, the proposed network differs from previous CNNs in the incorporation of a compact convolution module, which can be deployed with the constraints of mobile devices. As training data for the LiDAR and stereo fusion is rather limited, we introduce a simple yet effective approach for reproducing the raw KITTI dataset. The raw LiDAR scans are augmented by adapting an off-the-shelf stereo algorithm and a confidence measure. We evaluate the proposed network on the KITTI benchmark and data collected by our multi-sensor acquisition system. Experiments demonstrate that the proposed network generalizes across datasets and is significantly more accurate than various baseline approaches.
|Title of host publication||2018 IEEE International Conference on Robotics and Automation, ICRA 2018|
|Publisher||Institute of Electrical and Electronics Engineers Inc.|
|Number of pages||8|
|Publication status||Published - 2018 Sep 10|
|Event||2018 IEEE International Conference on Robotics and Automation, ICRA 2018 - Brisbane, Australia|
Duration: 2018 May 21 → 2018 May 25
|Name||Proceedings - IEEE International Conference on Robotics and Automation|
|Conference||2018 IEEE International Conference on Robotics and Automation, ICRA 2018|
|Period||18/5/21 → 18/5/25|
Bibliographical noteFunding Information:
This work was supported in part by the Institute for Information and communications Technology Promotion Grant through the Korea Government (MSIP) under Grant 2016-0-00197.
© 2018 IEEE.
All Science Journal Classification (ASJC) codes
- Control and Systems Engineering
- Artificial Intelligence
- Electrical and Electronic Engineering