IEEE Transactions on Vehicular Technology · 2007 · 22 citations · 14 references
ComputingAutomotive EngineeringComputer ScienceAutonomous VehiclesComputer VisionSensor FusionKalman FilteringLocalization UncertaintyMotion EstimationOptical FlowRobot LocalizationSensor Fusion For LocalizationLocalization Under Dynamic EnvironmentsMachine Vision SystemsObject LocalizationRobust LocalizationRobust Sensor FusionRobustnessSensor Fusion LocalizationSensor-level Fusion
In this paper, we use recently developed robust estimation ideas to improve object tracking by a stationary or nonstationary camera. Large uncertainties are always present in vision-based systems, particularly, in relation to the estimation of the initial state as well as the measurement of object motion. The robustness of these systems can be significantly improved by employing a robust extended Kalman filter (REKF). The system performance can also be enhanced by increasing the spatial diversity in measurements via employing additional cameras for video capture. We compare the performances of various image segmentation techniques in moving-object localization and show that normal-flow-based segmentation yields comparable results to, but requires significantly less time than, optical-flow-based segmentation. We also demonstrate with simulations that dynamic system modeling coupled with the application of an REKF significantly improves the estimation system performance, particularly, when subjected to large uncertainties.
14
Berthold K. P. Horn, Brian G. Schunck · Artificial Intelligence · 1981 · 9.9K citations · Full text
G. Uytterhoeven · Journal of Computational and Applied Mathematics · 1996 · 874 citations