Predicting depth from a monocular video sequence is an important task for autonomous driving. Although it has advanced considerably in the past few years, recent methods based on convolutional neural networks (CNNs) discard temporal coherence in the video sequence and estimate depth independently for each frame, which often leads to undesired inconsistent results over time. To address this problem, we propose to memorize temporal consistency in the video sequence, and leverage it for the task of depth prediction. To this end, we introduce a two-stream CNN with a flow-guided memory module, where each stream encodes visual and temporal features, respectively. The memory module, implemented using convolutional gated recurrent units (ConvGRUs), inputs visual and temporal features sequentially together with optical flow tailored to our task. It memorizes trajectories of individual features selectively and propagates spatial information over time, enforcing a long-term temporal consistency to prediction results. We evaluate our method on the KITTI benchmark dataset in terms of depth prediction accuracy, temporal consistency and runtime, and achieve a new state of the art. We also provide an extensive experimental analysis, clearly demonstrating the effectiveness of our approach to memorizing temporal consistency for depth prediction.
|Number of pages||11|
|Journal||IEEE Transactions on Intelligent Transportation Systems|
|Publication status||Published - 2020 Nov|
Bibliographical noteFunding Information:
Manuscript received March 29, 2019; revised June 19, 2019; accepted September 12, 2019. Date of publication September 25, 2019; date of current version October 30, 2020. This work was supported by Institute of Information & Communications Technology Planning & Evaluation (IITP) grant funded by the Korea government (MSIT) (2016-0-00197, Development of the high-precision natural 3D view generation technology using smart-car multi sensors and deep learning). The Associate Editor for this article was S. S. Nedevschi. (Corresponding author: Bumsub Ham.) The authors are with the School of Electrical and Electronic Engineering, Yonsei University, Seoul 03722, South Korea (e-mail: firstname.lastname@example.org; email@example.com; firstname.lastname@example.org). Digital Object Identifier 10.1109/TITS.2019.2942096
© 2000-2011 IEEE.
All Science Journal Classification (ASJC) codes
- Automotive Engineering
- Mechanical Engineering
- Computer Science Applications