Template matching methods applied to robot navigation assistance

This work was presented at the 2019 SPIE Optics Photonics conference: Marisol Rodriguez-Cuevas Victor H.
Diaz-Ramirez Rigoberto Juarez-Salazar and Kenia Picos Template matching methods for robot navigation assistance Proc.
SPIE 11136 Optics and Photonics for Information Processing XIII 111360K 6 September 2019 Abstract Template matching is an effective method for object recognition because it provides high accuracy in location estimation of targets and robustness to the presence of additive and nonoverlapping noise.
These features are useful for vision-based robot navigation where a reliable detection and location of scene objects is essential.
In this work the use of advanced template matched filters applied for robot navigation assistance is presented.
Several filters are constructed by the optimization of objective performance criteria.
These filters are exhaustively evaluated in synthetic image sequences and experimental scenes using a mobile robot in terms of efficiency of target detection accuracy of a target location and processing time. This work was developed at Instituto Politécnico Nacional - CITEDI Tijuana B.C.
Mexico.

Источник: rutube.ru