Early literacy in children begins through picture drawing and the subsequent sharing of an orally narrated story out of the drawn picture. This is the basis for the Picture Books story generation system whose motivation is to produce a textual counterpart of the input picture in order for the child to associate words with images. However, stories are comprised of sequences of events that occur ...

In this paper, a Cognitive Vision System (CVS) is presented, which explains the human behaviour of monitored scenes using naturallanguage texts. This cognitive analysis of human movements recorded in image sequences is here referred to as Human Sequence Evaluation (HSE) which defines a set of transformation modules involved in the automatic generation of semantic descriptions from pixel values....

This paper deals with motion capture of kinematic chains (e.g. human skeletons) from monocular image sequences taken by uncalibrated cameras. We present a method based on projecting an observation into a kinematic chain space (KCS). An optimization of the nuclear norm is proposed that implicitly enforces structural properties of the kinematic chain. Unlike other approaches our method does not r...

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...

This paper proposes a simple augmentation to texture mapping hardware which produces the correct depth buffer content and hence correct visibility when replacing complex objects by partially transparent textured polygons. Rendering such polygons exploits frame-to-frame coherence in image sequences of dynamic scenes. Correct depth values are obtained by keeping a small depth delta for every texe...

An adaptive approach to moving object recognition in image sequences from a single low{cost camera under egomotion is proposed. The object motion is restricted by ground plane trajectories. Quantitative and qualitative results of vehicle tracking in trac scenes are presented. It is demonstrated that acceptable results with a single low cost camera can be achieved for those objects, which are pr...

This paper describes an operational system which can acquire the core meanings of words without any prior knowledge of either the category or meaning of any words it encounters. The system is given as input, a description of sequences of scenes along with sentences which describe the [EVENTS] taking place as those scenes unfold, and produces as output, a lexicon consisting of the category and m...

The effect of reflection and transparency is superimposed in many real world scenes, which is caused by glass-like shiny and transparent materials. The presence of such incidental effect in a captured image has made it difficult to apply computer vision algorithms and has lead to erroneous results. Moreover, it disturbs the texture acquisition of the real-world scene. This paper presents an opt...

In theory HDR photography generated from exposure sequences is limited to pictures of still scenes preferably taken with the camera mounted on a tripod. Current state-of-the-art HDR imaging software relaxes this limitation by aligning the pictures with affine transformations. However, two pictures cannot be aligned with a single affine transformation if objects in the scene move or the position...

One of the goals of three-dimensional (3D) computer graphics is to create virtual realistic images of dynamically changing scenes. In this paper, we designed and implemented a system that processes multiple synchronized video sequences and generates 3D rendering of dynamic objects in real time. The videoimage-based virtual volumetric scene reconstruction system acquires synchronized multiple vi...