Object distance estimation algorithm for real-time FPGA-based stereoscopic vision system

Valery V. Strotov; Sergey A. Smirnov; Simon E. Korepanov; Alexey V. Cherpalkin

doi:10.1117/12.2324851

9 October 2018 Object distance estimation algorithm for real-time FPGA-based stereoscopic vision system

Valery V. Strotov, Sergey A. Smirnov, Simon E. Korepanov, Alexey V. Cherpalkin

Proceedings Volume 10792, High-Performance Computing in Geoscience and Remote Sensing VIII; 107920A (2018) https://doi.org/10.1117/12.2324851
Event: SPIE Remote Sensing, 2018, Berlin, Germany

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

Citation Download Citation

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

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available