Bewegungssteuerung durch Rechnersehen

Wünsche, Hans-Joachim

doi:10.1007/978-3-642-83562-9

Cited by 25 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…3D shape models exhibit the spatial distribution of visual features which allow objects to be recognized and tracked. In order to exploit both dynamical and shape models at the same time, the prediction error feedback scheme for recursive state estimation developed by Kalman and successors in the 1960's has been extended to image sequence processing by our group [2]. There are many publications on this approach so that only a short summary will be given here (see e.g., the survey articles [3,4]).…”

Section: The 4d-approach As the Core Of Expectation-driven Visionmentioning

confidence: 99%

See 1 more Smart Citation

A general dynamic vision architecture for UGV and UAV

Dickmanns

1992

Appl Intell

View full text Add to dashboard Cite

The expectation-based 4D approach to dynamic machine vision exploiting integral spatiotemporal models of objects in the real world is discussed in the application domains of unmanned ground and air vehicles. The method has demonstrated superior performance over the last half decade in autonomous road vehicle guidance with three different vans and busses, with an AGV on the factory floor and with completely autonomous relative state estimation for a twin turboprop aircraft in the landing approach to a runway without any external support; in all application areas only a small set of conventional microcomputers was sufficient for realizing the system. This shows the computational efficiency of the method combining both conventional engineering type algorithms and artificial intelligence components in a well balanced way.The modularity of the approach is demonstrated in a simulation set-up serving both the ground-and the air vehicle applications. Experimental results in both areas are discussed.

show abstract

Section: The 4d-approach As the Core Of Expectation-driven Visionmentioning

confidence: 99%

“…For improving numerical performance, the UD-factorized version of the square-root-filter is used [5]. Details may be found in [2,[6][7][8]. By exploiting the sparseness of the transition matrix in the dynamical models a speedup can be achieved.…”

Section: The 4d-approach As the Core Of Expectation-driven Visionmentioning

confidence: 99%

A general dynamic vision architecture for UGV and UAV

Dickmanns

1992

Appl Intell

View full text Add to dashboard Cite

show abstract

“…Wählt man den Zustandsvektor gemäß (17) so lautet das dynamische Modell des Roboters als allgemeine Vektordifferentialgleichung mit u^it) = lu.u^u^Y, (18) dem Eingangsvektor. Die Aufstellung der Systemmatrix F und der Steuermatrix G sowie die anschließende Diskretisierung des Systems erfolgt mit den für hneare Systeme gültigen Standardverfahren der Regelungstechnik, z.B.…”

unclassified

“…Die Wahl einer starren Grenze wirft daher Probleme auf.Mit Hilfe der Innovationskovarianz (Gl. (28)) läßt sich jedoch direkt eine an die augenblickliche Güte der Schätzung angepaßte und damit variable Fehlerschranke zur Störerkennung ableiten[17]. Der erste Term in Gl.…”

unclassified