Understanding the Spatial Organization of Image Regions by Means of Force Histograms: A Guided Tour

Matsakis, Pascal

doi:10.1007/978-3-7908-1752-2_5

Cited by 15 publications

(11 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The F-histogram, developed from the histogram of angles and first proposed by Matsakis in 1999 [28], is an effective way to build direction relationships between a pair of objects [30]. The F-histogram treats the image as a set of longitudinal sections instead of points, leading to rapid computation ( Figure 1).…”

Section: F-histogrammentioning

confidence: 99%

Scene Semantic Understanding Based on the Spatial Context Relations of Multiple Objects

Zhong

Zhao

2017

Remote Sensing

View full text Add to dashboard Cite

Abstract:As a result of the large semantic gap between the low-level features and the high-level semantics, scene understanding is a challenging task for high satellite resolution images. To achieve scene understanding, we need to know the contents of the scene. However, most of the existing scene classification methods, such as the bag-of-visual-words model (BoVW), feature coding, topic models, and neural networks, can only classify the scene while ignoring the components and the semantic and spatial relations between these components. Therefore, in this paper, a bottom-up scene understanding framework based on the multi-object spatial context relationship model (MOSCRF) is proposed to combine the co-occurrence relations and position relations at the object level. In MOSCRF, the co-occurrence relation features are modeled by the fisher kernel coding of objects (oFK), while the position relation features are represented by the multi-object force histogram (MOFH). The MOFH is the evolution of the force histogram between pairwise objects. The MOFH not only has the property of being invariant to rotation and mirroring, but also acquires the spatial distribution of the scene by calculating the acting force between multiple land-cover objects. Due to the utilization of the prior knowledge of the objects' information, MOSCRF can explain the objects and their relations to allow understanding of the scene. The experiments confirm that the proposed MOSCRF can reflect the layout mode of the scene both semantically and spatially, with a higher precision than the traditional methods.

show abstract

Section: F-histogrammentioning

confidence: 99%

Scene Semantic Understanding Based on the Spatial Context Relations of Multiple Objects

Zhong

Zhao

2017

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…The quality of descriptors extracted by histogram of angles or F-histogram was validated in several applicative contexts. Besides evaluation of spatial relations between objects, F-histograms have also been used for generating linguistic description of relations [BMK04], or for retrieving similar spatial relationships among images [Mat02]. However, directly exploiting them for localization task is impossible, because their definition is based on features extracted from a pair of objects.…”

Section: In the Image Processing Domainmentioning

confidence: 99%

Learning of fuzzy spatial relations between handwritten patterns

Delaye

Anquetil

2014

IJDMMM

View full text Add to dashboard Cite

“…By this approach of object approximation, temporal complexity decreases from n √ n to N log(N ) where n is number of pixels of objects under consideration and N is the number of vertex of object polygons. Temporal complexity for the said algorithm is not given but in general temporal complexity of force histograms is discussed in [9] for different object types. We assume same temporal complexity for objects because segmentation level problems raised by Matsakis forced the object as raster data and in addition to this algorithm for fuzzification of longitudinal sections increases temporal and computational complexity.…”

Section: Introductionmentioning

confidence: 99%

Spatial Relations Analysis by Using Fuzzy Operators

Salamat

Zahzah

2009

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Spatial relations play important role in computer vision, scene analysis, geographic information systems (GIS) and content based image retrieval. Analyzing spatial relations by Force histogram was introduced by Miyajima et al [1] and largely developed by Matsakis [2] who used a quantitative representation of relative position between 2D objects. Fuzzy Allen relations are used to define the fuzzy topological relations between different objects and to detect object positions in images. Concept for combined extraction of topological and directional relations by using histogram was developed by J. Malki and E.Zahzah [3], and further improved by Matsakis [4]. This algorithm has high computational and temporal complexity due to its limitations of object approximations. In this paper fuzzy aggregation operators are used for information integration along with polygonal approximation of objects. This approach gives anew, with low temporal and computational complexity of algorithm for the extraction of topological and directional relations.

show abstract

Understanding the Spatial Organization of Image Regions by Means of Force Histograms: A Guided Tour

Cited by 15 publications

References 9 publications

Scene Semantic Understanding Based on the Spatial Context Relations of Multiple Objects

Scene Semantic Understanding Based on the Spatial Context Relations of Multiple Objects

Learning of fuzzy spatial relations between handwritten patterns

Spatial Relations Analysis by Using Fuzzy Operators

Contact Info

Product

Resources

About