Fuzzy approach for data association in image tracking.

García, Julio, et al. "Fuzzy approach for data association in image tracking.." Mathware and Soft Computing 10.2-3 (2003): 117-129. <http://eudml.org/doc/39254>.

@article{García2003,
abstract = {A fuzzy system has been developed to ponder update decisions both for the trajectories and shapes estimated for targets. It is embedded in an A-SMGCS Surveillance function for airport surface, based on video data processing, in charge of the automatic detection, identification and tracking of all interesting targets (aircraft and relevant ground vehicles). The tracking system captures a sequence of images, preprocesses them to extract the moving regions (blobs), and associates the blobs to tracks to estimate the number of targets in the scenario and their parameters. The system was initially built with a set of rules derived from performance analysis, and then a procedure based on neuro-fuzzy techniques was applied to automatically obtain rules from examples. A validation of learned system shows its capability to produce appropriate decisions. Results obtained with real data in representative ground operations show the system capabilities to solve complex scenarios and improve tracking accuracy.},
author = {García, Julio, Molina, José Manuel, Besada, Juan Alberto, Portillo, Javier I.},
journal = {Mathware and Soft Computing},
keywords = {Lógica difusa; Heurística; Procesamiento de imágenes; Visión artificial},
language = {eng},
number = {2-3},
pages = {117-129},
title = {Fuzzy approach for data association in image tracking.},
url = {http://eudml.org/doc/39254},
volume = {10},
year = {2003},
}

TY - JOUR
AU - García, Julio
AU - Molina, José Manuel
AU - Besada, Juan Alberto
AU - Portillo, Javier I.
TI - Fuzzy approach for data association in image tracking.
JO - Mathware and Soft Computing
PY - 2003
VL - 10
IS - 2-3
SP - 117
EP - 129
AB - A fuzzy system has been developed to ponder update decisions both for the trajectories and shapes estimated for targets. It is embedded in an A-SMGCS Surveillance function for airport surface, based on video data processing, in charge of the automatic detection, identification and tracking of all interesting targets (aircraft and relevant ground vehicles). The tracking system captures a sequence of images, preprocesses them to extract the moving regions (blobs), and associates the blobs to tracks to estimate the number of targets in the scenario and their parameters. The system was initially built with a set of rules derived from performance analysis, and then a procedure based on neuro-fuzzy techniques was applied to automatically obtain rules from examples. A validation of learned system shows its capability to produce appropriate decisions. Results obtained with real data in representative ground operations show the system capabilities to solve complex scenarios and improve tracking accuracy.
LA - eng
KW - Lógica difusa; Heurística; Procesamiento de imágenes; Visión artificial
UR - http://eudml.org/doc/39254
ER -