Road Scene Depth Estimation Based on Deep Convolutional Neural Networks

Jianzhong Yuan; Wujie Zhou; Ting Pan; Pengli Gu

doi:10.3788/LOP56.081501

Journals >Laser & Optoelectronics Progress >Volume 56 >Issue 8 >Page 081501 > Article

Laser & Optoelectronics Progress
Vol. 56, Issue 8, 081501 (2019)

Road Scene Depth Estimation Based on Deep Convolutional Neural Networks

Jianzhong Yuan¹, Wujie Zhou^1、2、*, Ting Pan¹, and Pengli Gu¹

Author Affiliations

¹ School of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou, Zhejiang 310023, China

² College of Information Science and Electronic Engineering, Zhejiang University, Hangzhou, Zhejiang 310027, China

show less

DOI: 10.3788/LOP56.081501 Cite this Article Set citation alerts

Jianzhong Yuan, Wujie Zhou, Ting Pan, Pengli Gu. Road Scene Depth Estimation Based on Deep Convolutional Neural Networks[J]. Laser & Optoelectronics Progress, 2019, 56(8): 081501 Copy Citation Text

show less

Fig. 1. Structural diagram of neural network

Download full size

Fig. 2. Two types of network blocks. (a) Identity_block; (b) Conv_block

Download full size

Fig. 3. Schematic of N-layer Dense_block

Download full size

Fig. 4. Schematic of TransitionUp

Download full size

Fig. 5. Experimental results. (a) RGB image; (b) ground truth; (c) depth prediction map

Download full size

Method	Accuracy (higher is better)	Error (lower is better)
Method	δ<1.25		δ<1.25²	δ<1.25³	R_rms	R_{log_rms}	E_lg
Ref. [24]	0.488	0.947	0.972		2.6440	0.272	0.167
Ref. [41]	0.674	0.943	0.972		2.4618	0.243	0.126
Ref. [42]	0.640	0.947	0.979		2.5193	0.247	0.134
Ref. [43]	0.634	0.916	0.945		2.8246	0.305	0.127
Ref. [44]	0.566	0.945	0.970		2.6507	0.264	0.145
Proposed	0.717	0.947	0.974		2.4225	0.234	0.111

Table 1. Depth estimation results on KITTI dataset

Method	Accuracy (higher is better)	Error (lower is better)
Method	δ<1.25		δ<1.25²	δ<1.25³	R_rms	R_{log_rms}	E_lg
Proposed	0.717	0.947	0.974		2.4225	0.234	0.111
Proposed1	0.696	0.941	0.971		2.3877	0.242	0.124
Proposed2	0.678	0.946	0.974		2.412	0.237	0.122

Table 2. Depth estimation results of slice experiment

Jianzhong Yuan, Wujie Zhou, Ting Pan, Pengli Gu. Road Scene Depth Estimation Based on Deep Convolutional Neural Networks[J]. Laser & Optoelectronics Progress, 2019, 56(8): 081501

Download Citation

Set citation alerts for the article

Tools

Set citation alerts for the article

Save the article for my favorites

Paper Information