Abstract We present a Deep Image Compression neural network that relies on side
information, which is only available to the decoder. We base our algorithm on the …

This paper investigates the role of color in global stereo matching approaches. In our
evaluation study, we build various energy functions by combining nine color spaces with …

Cette thèse se situe dans le cadre de la vision par ordinateur et concerne plus précisément
l'étape de mise en correspondance de pixels en stéréovision binoculaire. Cette étape …

Global algorithms currently represent the state-of-the-art in dense stereo matching. These
methods first set up an energy function. The energy function is then subject to optimization …

The main purpose of constructing Intelligent Vehicles is to increase the safety for all traffic
participants. The detection of pedestrians, as one of the most vulnerable category of road …

In this paper, we propose an original approach to colour correlation-based stereo matching
with mono-dimensional windows. The result of the algorithm is a quasi-dense disparity map …

In this paper is presented a region-based methodology for Digital Elevation Model
segmentation obtained from laser scanning data. The methodology is based on two …

Binocular stereovision is the process of recovering the depth information of a visual scene,
which makes it attractive for many applications like 3-D reconstruction, multiview video …

In this paper, we present a dense 3D reconstruction algorithm adapted to stereoscopic omni
directional sensors. Our main contributions are the generalization of global constraints to …

Significant colour discrepancies between stereo images have severe impacts on stereo
matching algorithms, which depend on colour similarity. To address this problem, a region …