Renaud Péteri

DynTex: A comprehensive database of dynamic textures

We present the DynTex database of high-quality dynamic texture videos. It consists of over 650 sequences of dynamic textures, mostly in everyday surroundings. Additionally, we propose a scheme for the manual annotation of the sequences based on a detailed analysis of the physical processes underlying the dynamic textures. Using this scheme we describe the texture sequences in terms of both visual structure and semantic content. The videos and annotations are made publicly available for scientific research.

A Comparison of Wavelet Based Spatio-temporal Decomposition Methods for Dynamic Texture Recognition

This paper presents four spatio-temporal wavelet decompositions for characterizing dynamic textures. The main goal of this work is to compare the influence of spatial and temporal variables in the wavelet decomposition scheme. Its novelty is to establish a comparison between the only existing method [11] and three other spatio-temporal decompositions. The four decomposition schemes are presented and successfully applied on a large dynamic texture database. Construction of feature descriptors are tackled as well their relevance, and performances of the methods are discussed. Finally, future prospects are exposed.

Characterization and recognition of dynamic textures based on the 2D+T curvelet transform

The research context of this article is the recognition and description of dynamic textures. In image processing, the wavelet transform has been successfully used for characterizing static textures. To our best knowledge, only two works are using spatio-temporal multiscale decomposition based on the tensor product for dynamic texture recognition. One contribution of this article is to analyze and compare the ability of the 2D+T curvelet transform, a geometric multiscale decomposition, for characterizing dynamic textures in image sequences. Two approaches using the 2D+T curvelet transform are presented and compared using three new large databases. A second contribution is the construction of these three publicly available benchmarks of increasing complexity. Existing benchmarks are either too small not available or not always constructed using a reference database. Feature vectors used for recognition are described as well as their relevance, and performances of the different methods are discussed. Finally, future prospects are exposed.

Decomposition of Dynamic Textures Using Morphological Component Analysis

The research context of this paper is dynamic texture analysis and characterization. Many dynamic textures can be modeled as large scale propagating wavefronts and local oscillating phenomena. After introducing a formal model for dynamic textures, the morphological component analysis (MCA) approach with a well-chosen dictionary is used to retrieve the components of dynamic textures. We define two new strategies for adaptive thresholding in the MCA framework, which greatly reduce the computation time when applied on videos. Tests on real image sequences illustrate the efficiency of the proposed method. An application to global motion estimation is proposed and future prospects are finally exposed.

Tracking dynamic textures using a particle filter driven by intrinsic motion information

In this paper, a new method for tracking dynamic textures is presented. Its novelty is to use a particle filter driven by the intrinsic motion of the tracked dynamic texture. Many research works have indeed shown that dynamic textures are well characterized by their intrinsic motion (in proceedings of 4th international conference on computer recognition systems CORES’05, pp. 17–26, 2005). In this work, we compute motion statistics of dynamic textures and use them in the observation model of our particle filter. Our tracking method is successfully applied on test sequences. The algorithm is fast and is able to track a dynamic texture moving on another dynamic texture with different intrinsic dynamics. The method is also able to track a dynamic texture in cases where classical particle filters based on color information only fail. Comments and future prospects raised by this method are finally described.

A unique self-organization of bacterial sub-communities creates iridescence in Cellulophaga lytica colony biofilms

Iridescent color appearances are widespread in nature. They arise from the interaction of light with micron- and submicron-sized physical structures spatially arranged with periodic geometry and are usually associated with bright angle-dependent hues. Iridescence has been reported for many animals and marine organisms. However, iridescence has not been well studied in bacteria. Recently, we reported a brilliant “pointillistic” iridescence in colony biofilms of marine Flavobacteria that exhibit gliding motility. The mechanism of their iridescence is unknown. Here, using a multi-disciplinary approach, we show that the cause of iridescence is a unique periodicity of the cell population in the colony biofilm. Cells are arranged together to form hexagonal photonic crystals. Our model highlights a novel pattern of self-organization in a bacterial biofilm. ”Pointillistic” bacterial iridescence can be considered a new light-dependent phenomenon for the field of microbiology.

A 3D discrete curvelet based method for segmenting dynamic textures

This paper presents a new approach for segmenting a video sequence containing dynamic textures. The proposed method is based on a 2D+T curvelet transform and an octree hierarchical representation. The curvelet transform enables to outline spatio-temporal structures of a given scale and orientation. The octree structure based on motion coherence enables a better spatio-temporal segmentation than a direct application of the 2D+T curvelet transform. Our segmentation method is successfully applied on video sequences of dynamic textures. Future prospects are finally exposed.

Quantitatively Assessing Roads Extracted from High-Resolution Imagery

Urban mapping has become a challenge for scientists since the launch of high spatial resolution satellites. This paper focuses on the problem of quality when extracting roads from such data. The definition of a judicious reference enabling the establishment of quantitative criteria is proposed. A method is presented and two sets of criteria dedicated to the evaluation of road extraction algorithms are introduced. An example of an application is proposed enhancing the benefits of a rigorous approach of this problem.

Denoising 3d medical images using a second order variational model and wavelet shrinkage

The aim of this paper is to construct a model which decomposes a 3D image into two components: the first one containing the geometrical structure of the image, the second one containing the noise. The proposed method is based on a second order variational model and an undecimated wavelet thresholding operator. The numerical implementation is described, and some experiments for denoising a 3D MRI image are successfully performed. Future prospects are finally exposed.

Action recognition in videos using frequency analysis of critical point trajectories

This paper focuses on human action recognition in video sequences. A method based on the optical flow estimation is presented, where critical points of the flow field are extracted. Multi-scale trajectories are generated from those points and are characterized in the frequency domain. Finally, a sequence is described by fusing this frequency information with motion orientation and shape information. Experiments show that this method has recognition rates among the highest in the state of the art on the KTH dataset. Contrary to recent dense sampling strategies, the proposed method only requires critical points of motion flow field, thus permitting a lower computation time and a better sequence description. Results and perspectives are then discussed.