Rigid Part Decomposition in a Graph Pyramid

Artner, Nicole M.; Ion, Adrian; Kropatsch, Walter G.

doi:10.1007/978-3-642-10268-4_89

Cited by 4 publications

(6 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Before a HSS can be built, a target object needs to be defined and suitable features describing the object have to be selected. This can be done automatically by methods like in [9–12] or semi-manually as for the experiments in this paper.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Multi-scale 2D tracking of articulated objects using hierarchical spring systems

Artner

Ion

Kropatsch

2011

Pattern Recognition

Self Cite

View full text Add to dashboard Cite

This paper presents a flexible framework to build a target-specific, part-based representation for arbitrary articulated or rigid objects. The aim is to successfully track the target object in 2D, through multiple scales and occlusions. This is realized by employing a hierarchical, iterative optimization process on the proposed representation of structure and appearance. Therefore, each rigid part of an object is described by a hierarchical spring system represented by an attributed graph pyramid. Hierarchical spring systems encode the spatial relationships of the features (attributes of the graph pyramid) describing the parts and enforce them by spring-like behavior during tracking. Articulation points connecting the parts of the object allow to transfer position information from reliable to ambiguous parts. Tracking is done in an iterative process by combining the hypotheses of simple trackers with the hypotheses extracted from the hierarchical spring systems.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Articulation points . They can be initialized manually (as in the following experiments) or automatically by observing the articulated motion of the target object [13,9] .…”

Section: Methodsmentioning

confidence: 99%

Multi-scale 2D tracking of articulated objects using hierarchical spring systems

Artner

Ion

Kropatsch

2011

Pattern Recognition

Self Cite

View full text Add to dashboard Cite

show abstract

“…Objects of interest are, however, mostly composed of several such regions and further grouping is required. In order to preserve the structure of points belonging to the same object pairwise relations like distances can be used efficiently to overcome failures caused by noise or occlusions (see [46,47]).…”

Section: Moving Objectsmentioning

confidence: 99%

“…In [47] a graph-pyramid is used to extract a moving articulated object from a video, and identify its rigid parts. First a spatio-temporal selection is performed, where the spatial relationships of tracked interest points over time are analysed and a triangulation is produced, with triangles labeled as potentially-rigid and non-rigid.…”

Section: Extraction Of Structure From Videosmentioning

confidence: 99%

“…Articulated objects are characterized by two or more rigid parts joint by articulation points. The nodes of the graph corresponding to the articulation point as well as the ones corresponding to the rigid parts are identified in the graph pyramid [47]. The nodes that compose each of the rigid parts will be merged in one apex in a certain pyramid level so that to follow the movement of each rigid part it is only needed to apply the geometric transformations in its apex and then doing the top-down reconstruction.…”

Section: Articulated Objectsmentioning

confidence: 99%

See 1 more Smart Citation

When Pyramids Learned Walking

Kropatsch

2009

Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications

Self Cite

View full text Add to dashboard Cite

A temporal image sequence increases the dimension of the data by simply stacking images above each other. This further raises the computational complexity of the processes. The typical content of a pixel or a voxel is its grey or color value. With some processing, features and fitted model parameters are added. In a pyramid these values are repeatedly summarized in the stack of images or image descriptions with a constant factor of reduction. From this derives their efficiency of allowing log(diameter) complexity for global information transmission. Content propagates bottom-up by reduction functions like inheritance or filters. Content propagates top-down by expansion functions like interpolation or projection. Moving objects occlude different parts of the image background. Computing one pyramid per frame needs lots of bottomup computation and very complex and time consuming updating. In the new concept we propose one pyramid per object and one pyramid for the background. The connection between both is established by coordinates that are coded in the pyramidal cells much like in a Laplacian pyramid or a wavelet. We envision that this code will be stored in each cell and will be invariant to the basic movements of the object. All the information about position and orientation of the object is concentrated in the apex. New positions are calculated for the apex and can be accurately reconstructed for every cell in a top-down process. At the new pixel locations the expected content can be verified by comparing it with the actual image frame.

show abstract