Translator Disclaimer
Presentation + Paper
9 October 2018 Object distance estimation algorithm for real-time FPGA-based stereoscopic vision system
Author Affiliations +
Abstract
This paper describes the complex object distance measuring algorithm for the stereoscopic real-time onboard vision system. This complex algorithm includes two correlation-based algorithms with the different performance complexity and accuracy. The most accurate basic algorithm is a two-dimensional template matching procedure. The other basic algorithm is one-dimensional matching algorithm that used cumulative images as an input. The switching between the algorithms is based on the proposed algorithm performance indicator. This indicator is based on the mean object and background brightness comparison. The experimental research was performed using a set of artificial and natural video sequences. The proposed complex estimation algorithm showed good accuracy in all case studies. The real-time performance of the algorithm in FPGA-based vision system was demonstrated.
Conference Presentation
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Valery V. Strotov, Sergey A. Smirnov, Simon E. Korepanov, and Alexey V. Cherpalkin "Object distance estimation algorithm for real-time FPGA-based stereoscopic vision system", Proc. SPIE 10792, High-Performance Computing in Geoscience and Remote Sensing VIII, 107920A (9 October 2018); https://doi.org/10.1117/12.2324851
PROCEEDINGS
8 PAGES + PRESENTATION

SHARE
Advertisement
Advertisement
Back to Top