TY  - JOUR
AU  - Cristhian A. Aguilera-Carrasco
AU  - Cristhian Aguilera
AU  - Cristobal A. Navarro
AU  - Angel Sappa
PY  - 2020//
TI  - Fast CNN Stereo Depth Estimation through Embedded GPU Devices
T2  - SENS
JO  - Sensors
SP  - 3249
VL  - 20
IS  - 11
KW  - stereo matching
KW  - deep learning
KW  - embedded GPU
N2  - Current CNN-based stereo depth estimation models can barely run under real-time constraints on embedded graphic processing unit (GPU) devices. Moreover, state-of-the-art evaluations usually do not consider model optimization techniques, being that it is unknown what is the current potential on embedded GPU devices. In this work, we evaluate two state-of-the-art models on three different embedded GPU devices, with and without optimization methods, presenting performance results that illustrate the actual capabilities of embedded GPU devices for stereo depth estimation. More importantly, based on our evaluation, we propose the use of a U-Net like architecture for postprocessing the cost-volume, instead of a typical sequence of 3D convolutions, drastically augmenting the runtime speed of current models. In our experiments, we achieve real-time inference speed, in the range of 5–32 ms, for 1216 × 368 input stereo images on the Jetson TX2, Jetson Xavier, and Jetson Nano embedded devices.
UR  - https://www.mdpi.com/1424-8220/20/11/3249
L1  - http://refbase.cvc.uab.es/files/AAN2020.pdf
UR  - http://dx.doi.org/10.3390/s20113249
N1  - MSIAU; 600.122
ID  - Cristhian A. Aguilera-Carrasco2020
ER  -