From Partition Trees to Semantic Trees

Giró, Xavier; Marqués, Ferran

doi:10.1007/11848035_41

Cited by 2 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Except for a few contributions in the field of object recognition [33,34,35], BPTs were mainly used for segmentation / classification tasks, where such total partitions make sense from a semantic point of view. More precisely, the wider application field of BPTs is remote sensing [36].…”

Section: Binary Partition Treesmentioning

confidence: 99%

Binary Partition Tree construction from multiple features for image segmentation

Randrianasoa

Kurtz

Desjardin

et al. 2018

Pattern Recognition

View full text Add to dashboard Cite

In the context of image analysis, the Binary Partition Tree (BPT) is a classical data structure for the hierarchical modeling of images at different scales. BPTs belong both to the families of graph-based models and morphological hierarchies. They constitute an efficient way to define sets of nested partitions of image support, that further provide knowledge-guided reduced research spaces for optimization-based segmentation procedures. Basically, a BPT is built in a mono-feature way, i.e. for one given image, and one given metric, by merging pairs of connected image regions that are similar in the induced feature space. Our goal is to design a new family of BPTs, dealing with the need to directly manage multiple features within its building process. Then, we propose a generalization of the BPT construction framework, allowing one to embed multiple features. The cornerstone of our approach relies on a collaborative strategy used to establish a consensus between different metrics, thus enabling to obtain a unified hierarchical segmentation space. In particular, this provides alternatives to the complex issue of metric construction from several-possibly non-comparable-features. To reach that goal, we first revisit the BPT construction algorithm to describe it in a graph-based formalism. Then, we present the structural and algorithmic evolutions and impacts when embedding multiple features in BPT construction. Final experiments illustrate how this multi-feature framework can be used to build BPTs from multiple metrics computed through the (potentially multiple) image content(s).

show abstract

Section: Binary Partition Treesmentioning

confidence: 99%

Binary Partition Tree construction from multiple features for image segmentation

Randrianasoa

Kurtz

Desjardin

et al. 2018

Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Each valid combination with a confidence over the preset threshold is considered a valid instance of the Laptop class. A more detailed description of the detection algorithm can be found in [8]. …”

Section: Detection Algorithmmentioning

confidence: 99%

Composite Object Detection in Video Sequences: Application to Controlled Environments

Giró

Marqués

2007

Eighth International Workshop on Image Analysis for Multimedia Interactive Services (WIAMIS '07)

Self Cite

View full text Add to dashboard Cite

This paper presents a set of techniques for the detection of composite objects in video recordings of a controlled environment. Firstly, a selective region-based analysis is performed by tuning the algorithm to the perceptual characteristics of the object in the environment. Secondly, the controlled perceptual and semantic variabilities of the object are addressed by the detection analysis thanks to a frame by frame update of the object models, and by allowing multiple models for a single object. The proposed techniques are illustrated in the detection of laptops from a zenithal view in a smart room.

show abstract

From Partition Trees to Semantic Trees

Cited by 2 publications

References 7 publications

Binary Partition Tree construction from multiple features for image segmentation

Binary Partition Tree construction from multiple features for image segmentation

Composite Object Detection in Video Sequences: Application to Controlled Environments

Contact Info

Product

Resources

About