Fuzzy directional enlacement landscapes for the evaluation of complex spatial relations

Clément, Michel; Kurtz, Camille; Wendling, Laurent

doi:10.1016/j.patcog.2019.107185

“…Early researchers used fuzzy model-based approaches to represent spatial constraints among objects. Fuzzy set is crucial to take into account the imprecision inherent to images [11], [12]. After that, spatial descriptor-based approaches were proposed to model spatial relation which take fuzzy model into account.…”

Section: Related Workmentioning

confidence: 99%

Spatial-Semantic Transformer for Spatial Relation Recognition

Peng,

Wang,

Ge

2023

J. Phys.: Conf. Ser.

0

View full text Add to dashboard Cite

Spatial relation recognition, which aims to predict a spatial relation predicate, has attracted increasing attention in the computer vision study. During tackling this problem, modeling spatial relation of the subjects and objects is of great importance. We find that only using spatial features leads to poor results in predicting the spatial relation. To overcome these challenges, we propose an effective spatial attention module to enhance spatial features using semantic features. After identifying the importance of spatial attention mechanism, we propose a spatial transformer module with encoder layers to recognize unseen spatial relation based on spatial attention mechanism. Extensive experiments on the benchmark dataset (SpatialSense) show that, by using refined spatial feature, our spatial transformer model and spatial attention model achieve state-of-the-art performance on overall accuracy.

show abstract

“…This approach can provide an evaluation as two extreme values and an average value. In 27 , a fuzzy landscape model is proposed, which allows to visualize and evaluate this relation directly in the image space.…”

Section: Introductionmentioning

confidence: 99%

A new representation method of the relative position between objects in the image based on the histogram of position sensing forces

Tian

2024

Sci Rep

1

0

View full text Add to dashboard Cite

Let the computer apprehend and describe the representation of the relative position between objects of the image by the way of the common intuition of the human is an important task of the computer vision and pattern recognition. To complete this task, the position sensing parameter and histogram of position sensing forces are proposed in this paper. The position sensing parameter can represent the spatial relative position of the point with regard to the reference object, and the point is from the argument object. The histogram of position sensing forces is composed of the position sensing parameter of each point in the argument object and the gravitational forces between each point of the argument object and each point of the reference object. The histogram of position sensing forces can simulate the human perception for the directional spatial relations between the argument object and reference object of the image, considering the shape, size, angular and metric information of the spatial object.

show abstract

“…This approach can provide an evaluation as two extreme values and an average value. In [27], a fuzzy landscape model is proposed that allows both to visualize and evaluate this relation directly in the image space, following different directions.…”

Section: Introductionmentioning

confidence: 99%

Representation of the relative position between objects in the image: histogram of position sensing forces

Tian

2023

Preprint

0

View full text Add to dashboard Cite

Let the computer apprehend and describe the representation of the relative position between objects of the image by the way of the common intuition of the human is an important task of the computer vision and pattern recognition. To complete this task, the position sensing parameter and histogram of position sensing forces are proposed in this paper. The position sensing parameter can represent the spatial relative position of the point with regard to the reference object, and the point is from the argument object. The histogram of position sensing forces is composed of the position sensing parameter of each point in the argument object and the gravitational forces between each point of the argument object and each point of the reference object. The histogram of position sensing forces can simulate the human perception for the directional spatial relations between the argument object and reference object of the image, considering the shape, size, angular and metric information of the spatial object.

show abstract

Fuzzy directional enlacement landscapes for the evaluation of complex spatial relations

Cited by 4 publications

References 34 publications

Spatial-Semantic Transformer for Spatial Relation Recognition

Spatial-Semantic Transformer for Spatial Relation Recognition

A new representation method of the relative position between objects in the image based on the histogram of position sensing forces

Representation of the relative position between objects in the image: histogram of position sensing forces

Contact Info

Product

Resources

About