Multi-level Object Population Analysis with an Embedded MPP Model

Csaba Benedek ()
Additional contact information
Csaba Benedek: Institute for Computer Science and Control (SZTAKI)

Chapter Chapter 6 in Multi-Level Bayesian Models for Environment Perception, 2022, pp 155-186 from Springer

Abstract: Abstract In this chapter, we introduce a probabilisticMarked Point Process (MPP) approach for extracting complex hierarchical object structures from digital images used by various vision applications. The proposed framework extends conventional Marked Point Process (MPP)Marked Point Process (MPP) models by including object-subobject ensembles in parent–child relationships, and creating coherent object groups from corresponding objects, by a Bayesian partitioning of the patent entity population. Unlike former, largely domain-specific attempts on MPPMarked Point Process (MPP) generalization, the proposed method is defined at an abstract level, while it provides simple and clear interfaces for the possible applications. We also introduce a global optimization process for the multi-layer framework, which attempts to find the optimal configuration of entities, considering the image data (observation), prior knowledge-based constraints, and interactions between the neighboring and the hierarchically related objects. The efficiency of the proposed method is demonstrated in three different application areas qualitatively and quantitatively: built-in area analysis in remotely sensed images, traffic monitoringTraffic monitoring on airborne LidarLight Detection and Ranging (Lidar) data and optical circuit inspection.

Date: 2022
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:sprchp:978-3-030-83654-2_6

Ordering information: This item can be ordered from
http://www.springer.com/9783030836542

DOI: 10.1007/978-3-030-83654-2_6

Access Statistics for this chapter

More chapters in Springer Books from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().