Evaluation of aerial pictures is of key importance for environmental analysis given the large extensions of land to study. This paper focuses on texture based segmentation of aerial images and characterisation of landscapes. Characterisation is achieved by means of a histogram of microtexture LBP/C vectors. Segmentations is hierarchically performed in a top down way by comparing the textures of...

Scene analysis is a major aspect of perception and continues to challenge machine perception. This paper addresses the scene-analysis problem by integrating a primitive segmentation stage with a model of associative memory. The model is a multistage system that consists of an initial primitive segmentation stage, a multimodule associative memory, and a short-term memory (STM) layer. Primitive s...

Scene understanding and other high-level visual tasks usually rely on segmenting the captured images for dealing with a more efficient mid-level representation. Although this segmentation stage will consider topological constraints for the set of obtained regions (e.g., their internal connectivity), it is typical that the importance of preserving the topological relationships among regions will...

Image segmentation and 3D pose estimation are two key cogs in any algorithm for scene understanding. However, state-of-the-art CRF-based models for image segmentation rely mostly on 2D object models to construct top-down high-order potentials. In this paper, we propose new topdown potentials for image segmentation and pose estimation based on the shape and volume of a 3D object model. We show t...

Image and, more recently, video segmentation form an important part of image understanding. Several algorithms presuppose that this step is efficiently and correctly completed by an oracle. A recent bottom up image segmentation algorithm incorporates both local and global information in an image and runs fast in practice. This algorithm is loosely based on Kruskal’s algorithm on minimum spannin...

For the present application, which was concerned with detection and characterisation of blood vesse l s on angiograms, subsequent grouping was res tr ic ted to anti-symmetric edge sections which formed a ridge with high grey v a l u e s in the centre. The ridges corresponded closely with blood ves se l s shown in the image. The width of each ridge and the locus of i t s centreline were d e r i ...

We derive a convex optimization problem for the task of segmenting sequential data, which explicitly treats presence of outliers. We describe two algorithms for solving this problem, one exact and one a top-down novel approach, and we derive a consistency results for the case of two segments and no outliers. Robustness to outliers is evaluated on two real-world tasks related to speech segmentat...

Automatic segmentation of images, means being able to automatically divide an image into parts that can be analysed to give meaning. In segmentation of faces, the goal is to locate the features of the face that describes it shape. These are features like mouth, nose, eyes, eyebrows and jawline. This report describes the implementation and the theory behind a tool that does face segmentation usi...