PMID- 30583606
OWN - NLM
STAT- PubMed-not-MEDLINE
DCOM- 20190103
LR  - 20231005
IS  - 1424-8220 (Electronic)
IS  - 1424-8220 (Linking)
VI  - 19
IP  - 1
DP  - 2018 Dec 23
TI  - Depth from a Motion Algorithm and a Hardware Architecture for Smart Cameras.
LID - 10.3390/s19010053 [doi]
LID - 53
AB  - Applications such as autonomous navigation, robot vision, and autonomous flying 
      require depth map information of a scene. Depth can be estimated by using a 
      single moving camera (depth from motion). However, the traditional depth from 
      motion algorithms have low processing speeds and high hardware requirements that 
      limit the embedded capabilities. In this work, we propose a hardware architecture 
      for depth from motion that consists of a flow/depth transformation and a new 
      optical flow algorithm. Our optical flow formulation consists in an extension of 
      the stereo matching problem. A pixel-parallel/window-parallel approach where a 
      correlation function based on the sum of absolute difference (SAD) computes the 
      optical flow is proposed. Further, in order to improve the SAD, the curl of the 
      intensity gradient as a preprocessing step is proposed. Experimental results 
      demonstrated that it is possible to reach higher accuracy (90% of accuracy) 
      compared with previous Field Programmable Gate Array (FPGA)-based optical flow 
      algorithms. For the depth estimation, our algorithm delivers dense maps with 
      motion and depth information on all image pixels, with a processing speed up to 
      128 times faster than that of previous work, making it possible to achieve high 
      performance in the context of embedded applications.
FAU - Aguilar-Gonzalez, Abiel
AU  - Aguilar-Gonzalez A
AUID- ORCID: 0000-0002-4941-9967
AD  - Instituto Nacional de Astrofisica, Optica y Electronica (INAOE), Tonantzintla 
      72840, Mexico. abiel@inaoep.mx.
AD  - Institut Pascal, Universite Clermont Auvergne (UCA), 63178 Clermont-Ferrand, 
      France. abiel@inaoep.mx.
FAU - Arias-Estrada, Miguel
AU  - Arias-Estrada M
AD  - Instituto Nacional de Astrofisica, Optica y Electronica (INAOE), Tonantzintla 
      72840, Mexico. ariasmo@inaoep.mx.
FAU - Berry, Francois
AU  - Berry F
AD  - Institut Pascal, Universite Clermont Auvergne (UCA), 63178 Clermont-Ferrand, 
      France. francois.berry@uca.fr.
LA  - eng
PT  - Journal Article
DEP - 20181223
PL  - Switzerland
TA  - Sensors (Basel)
JT  - Sensors (Basel, Switzerland)
JID - 101204366
PMC - PMC6338951
OTO - NOTNLM
OT  - FPGA (Field Programmable Gate Array)
OT  - depth estimation
OT  - monocular systems
OT  - optical flow
OT  - smart cameras
COIS- The authors declare no conflict of interest.
EDAT- 2018/12/26 06:00
MHDA- 2018/12/26 06:01
PMCR- 2019/01/01
CRDT- 2018/12/26 06:00
PHST- 2018/11/03 00:00 [received]
PHST- 2018/11/27 00:00 [revised]
PHST- 2018/11/29 00:00 [accepted]
PHST- 2018/12/26 06:00 [entrez]
PHST- 2018/12/26 06:00 [pubmed]
PHST- 2018/12/26 06:01 [medline]
PHST- 2019/01/01 00:00 [pmc-release]
AID - s19010053 [pii]
AID - sensors-19-00053 [pii]
AID - 10.3390/s19010053 [doi]
PST - epublish
SO  - Sensors (Basel). 2018 Dec 23;19(1):53. doi: 10.3390/s19010053.