Traffic Scene Depth Analysis Based on Depthwise Separable Convolutional Neural Network

Table 1

Depth estimation results on the KITTI data set.

Method	Accuracy (higher is better)			Error (lower is better)
				rms	log_rms	log10
Xie et al. [26]	0.488	0.947	0.972	2.6440	0.272	0.167
Laina et al. [9]	0.674	0.943	0.972	2.4618	0.243	0.126
Yin et al. [27]	0.640	0.947	0.979	2.5193	0.247	0.134
Dimitrievski et al. [40]	0.634	0.916	0.945	2.8246	0.305	0.127
Mancini et al. [25]	0.566	0.945	0.970	2.6507	0.264	0.145
Proposed1	0.693	0.949	0.975	2.3993	0.232	0.117
Proposed2	0.691	0.949	0.976	2.3676	0.231	0.117
Proposed3	0.699	0.949	0.975	2.3786	0.232	0.116