We describe a method to completely automatically recover 3D scene structure together with a camera for each frame from a sequence of images acquired by an unknown camera undergoing unknown movement. Previous approaches have used calibration objects or landmarks to recover this information, and are therefore often limited to a particular scale. The approach of this paper is far more general, sin...

In a visual driver-assistance system, road sign detection and tracking is one of the major tasks. This study describes an approach to detecting and tracking road signs appearing in complex traffic scenes. In the detecting phase, two neural networks are developed to extract color and shape features of traffic signs, respectively, from the input scene images. Traffic signs are then located in the...

Psychophysical thresholds were measured for discriminating small changes in spatial features of naturalistic scenes (morph sequences), for foveal and peripheral vision, and under M-scaling. Sensitivity was greatest for scenes with near natural Fourier amplitude slope, perhaps implying that human vision is optimised for natural scene statistics. A low-level model calculated differences in local ...

We propose a system for robust modeling and visualisation of complex outdoor scenes from multi-camera image sequences and additional sensor information. A camera rig with one or more fire-wire cameras is used in conjunction with a 3-axis rotation sensor to robustly obtain a calibration of the scene with an uncalibrated structure from motion approach. Dense depth maps are estimated with multi-vi...

This paper presents a recent work in human behaviour representation and on-line recognition for video interpretation. We propose a declarative model to represent human behaviours and we use the logic-based approach to recognise predefined behaviour models. We demonstrate our representation formalism and the inference engine on two video sequences. We also propose a limit for the number of behav...

In this paper we introduce a complete framework to automatically generate "cinematographic view" of dynamic scenes in real-time. The main goal of such a system is to provide a succession of shots and sequences (of virtual dynamic scenes) that can be related to pure cinema. Our system is based on the use of an image-based control of the camera that allows different levels of visual tasks and a m...

Currently, there is a great interest in the study of three-dimensional reconstruction from digital images. The applications of photogrammetric algorithms has allowed us significant improvements in procedures of camera calibration, movement of objects in scenes, shape from shading and range images. The procedure of the distance estimation from simple images is important to find the depth measure...

The analysis of 3D scenes consisting of nonrigid moving objects from 2D image sequences is discussed. A parametric description of dynamic objects is extracted and the time variant scene parameters are estimated throughout the sequence by employing an analysis by synthesis approach. From the parametric scene description images are synthesized and compared with the original input images of the ca...

The dynamic content of physical scenes is largely compositional, that is, the movements of the objects and of their parts are hierarchically organised and relate through composition along this hierarchy. This structure also prevails in the apparent 2D motion that a video captures. Accessing this visual motion hierarchy is important to get a better understanding of dynamic scenes and is useful f...

Despite the recent developments in spatiotemporal local features for action recognition in video sequences, local color information has so far been ignored. However, color has been proved an important element to the success of automated recognition of objects and scenes. In this paper we extend the space-time interest point descriptor STIP to take into account the color information on the featu...