A technique for building databases of annotated and realistic human silhouettes based on an avatar

in Annual Workshop on Circuits, Systems and Signal Processing (ProRISC) (2009, November)

The real-time interpretation of video scenes and human motion is a research field with a lot of applications. Awidely used pre-processing step is the background subtraction, which highlights silhouettes ... [more ▼]

The real-time interpretation of video scenes and human motion is a research field with a lot of applications. Awidely used pre-processing step is the background subtraction, which highlights silhouettes. In addition, example-based and learning-based approaches are attractive for the interpretation of complex scenes. But to be effective, such techniques need to be trained on samples of realistic human silhouettes. This paper presents a method to automatically build databases of artificial, realistic, and annotated human silhouettes. Our method, based on a 3D human avatar, allows to save additional data with the silhouettes, and to highlight the different body parts. These supplementary data may be application-driven. To help in evaluating the relevance of automatically generated databases, we suggest some practical solutions based on a visual signature of the databases. [less ▲]

Techniques to improve the foreground segmentation with a 3D camera and a color camera

(2009, November)

Nowadays, techniques for real-time interpretation of video scenes are widespread. Amongst these techniques, the foreground segmentation is one of the favorite. It can be applied to color images as well as ... [more ▼]

Nowadays, techniques for real-time interpretation of video scenes are widespread. Amongst these techniques, the foreground segmentation is one of the favorite. It can be applied to color images as well as depth maps. The point of using depth maps is straightforward as a single color camera is not able to provide depth information. Technologies capable to acquire 3D informations are thus adequate to complement color cameras in consumer products. Practice has shown that 3D or RGB signals, taken alone, are unreliable to extract the foreground under arbitrary conditions. Therefore we combine both modalities to counter the intrinsic limitations of both modalities, which is only possible if the problems specific to a technology are handled appropriately. This paper presents a new global approach for enhanced foreground segmentation that handles limitations to 3D and RGB in a combined way. [less ▲]

Combining Color, Depth, and Motion for Video Segmentation

in Computer Vision Systems (2009, October)

This paper presents an innovative method to interpret the content of a video scene using a depth camera. Cameras that provide distance instead of color information are part of a promising young technology ... [more ▼]

This paper presents an innovative method to interpret the content of a video scene using a depth camera. Cameras that provide distance instead of color information are part of a promising young technology but they come with many diff culties: noisy signals, small resolution, and ambiguities, to cite a few. By taking advantage of the robustness to noise of a recent background subtraction algorithm, our method is able to extract useful information from the depth signals. We further enhance the robustness of the algorithm by combining this information with that of an RGB camera. In our experiments, we demonstrate this increased robustness and conclude by showing a practical example of an immersive application taking advantage of our algorithm. [less ▲]

Anchors of morphological operators and algebraic openings

in Hawkes, Peter (Ed.) Advances in Imaging and Electron Physics (2009)

Opening and closing operators play an important role in the field of mathematical morphology, mainly because of their useful property of idempotence, which is similar to the notion of ideal filter in ... [more ▼]

Opening and closing operators play an important role in the field of mathematical morphology, mainly because of their useful property of idempotence, which is similar to the notion of ideal filter in linear filtering. From a theoretical point of view, the study of openings has focused on the algebraic characterization of the operators themselves. Morphological filters have been studied for more than 30 years; the effects of the first filters (erosions, openings, and so on) are known in depth. In discussing the effects of a filter, it is not only the operator that is studied but also its relationship with the processed function or image and, in the particular case of mathematical morphology, the structuring element. In addition, there are several approaches to this analysis. For example, the analysis can consider the whole function or some subparts of the function, as in Van Droogenbroeck and Buckley (2005), who introduced the notion of morphological anchors. Anchors were defined in the context of morphological openings, as defined by the cascade of an erosion followed by a dilation. The extension to other kinds of openings is not straightforward. Despite the fact that all morphological openings induce the appearance of anchors, some opening operators (like the quantization opening defined in this chapter) might have no anchors. This chapter presents the theory of anchors related to morphological erosions and openings, and establishes some properties for the extended scope of algebraic openings. It is shown under which circumstances anchors exist for algebraic openings and how to locate some anchors; for example, it suffices for an opening to be spatial or shift-invariant to guarantee the existence of anchors. As for morphological openings, the existence of anchors may help clarify some algorithms or lead to new algorithms to compute algebraic openings. [less ▲]

ViBe: a powerful random technique to estimate the background in video sequences

in International Conference on Acoustics, Speech, and Signal Processing (ICASSP 2009) (2009, April)

Background subtraction is a crucial step in many automatic video content analysis applications. While numerous acceptable techniques have been proposed so far for background extraction, there is still a ... [more ▼]

Background subtraction is a crucial step in many automatic video content analysis applications. While numerous acceptable techniques have been proposed so far for background extraction, there is still a need to produce more efficient algorithms in terms of adaptability to multiple environments, noise resilience, and computation efficiency. In this paper, we present a powerful method for background extraction that improves in accuracy and reduces the computational load. The main innovation concerns the use of a random policy to select values to build a samples-based estimation of the background. To our knowledge, it is the first time that a random aggregation is used in the field of background extraction. In addition, we propose a novel policy that propagates information between neighboring pixels of an image. Experiment detailed in this paper show how our method improves on other widely used techniques, and how it outperforms these techniques for noisy images. [less ▲]

Frontal-view gait recognition by intra- and inter-frame rectangle size distribution

in Pattern Recognition Letters (2009), 30

Current trends seem to accredit gait as a sensible biometric feature for human identification, at least in a multimodal system. In addition to being a robust feature, gait is hard to fake and requires no ... [more ▼]

Current trends seem to accredit gait as a sensible biometric feature for human identification, at least in a multimodal system. In addition to being a robust feature, gait is hard to fake and requires no cooperation from the user. As in many video systems, the recognition confidence relies on the angle of view of the camera and on the illumination conditions, inducing a sensitivity to operational conditions that one may wish to lower. In this paper we present an efficient approach capable of recognizing people in frontal-view video sequences. The approach uses an intra-frame description of silhouettes which consists of a set of rectangles that will fit into any closed silhouette. A dynamic, inter-frame, dimension is then added by aggregating the size distributions of these rectangles over multiple successive frames. For each new frame, the inter-frame gait signature is updated and used to estimate the identity of the person detected in the scene. Finally, in order to smooth the decision on the identity, a majority vote is applied to previous results. In the final part of this article, we provide experimental results and discuss the accuracy of the classification for our own database of 21 known persons, and for a public database of 25 persons. [less ▲]

Analyse et conception des systèmes de télécommunications

Learning material (2008)

Principes des télécommunications analogiques et numériques

Learning material (2008)

Traitement numérique des images (transparents)

Learning material (2007)

Principes de base du réseau GSM et des transmissions GPRS

Conference given outside the academic context (2006)