Detecting automatically a person who needs help in a shopping center represents an unique challenge in computer vision. It lies in the poor quality of images we consider. Our method focuses on consistency of dense optical flow to extract head turns.

We propose a method for unsupervised video object segmentation by transferring the knowledge encapsulated in image-based instance embedding networks. The instance embedding network produces an embedding vector for each pixel that enables identifying all pixels belonging to the same object. Though trained on static images, the instance embeddings are stable over consecutive video frames, which a...

Dynamic textures can be considered to be spatio-temporally varying visual patterns in image sequences with certain temporal regularity. We propose a novel and efficient approach to explore the violation of the brightness constancy assumption, as an indication of presence of dynamic texture, using simple optical flow techniques. We assume that dynamic texture regions are those that have poor spa...

In analysis of the brain and visual system functionality, scientific evidence points to two independent processing pathways in recognising biological movement, i.e. dorsal and ventral streams. Motion information generated in the dorsal processing stream is presented as fuzzy optical flow division while ventral processing stream with information of the object form is implemented as an active bas...

Cardiac Motion artifacts in PET are a well known problem. The heart undergoes two types of motion, the motion due to respiratory displacement and the motion due to cardiac contraction. These movements lead to blurring of data and to inaccuracies in the quantification. In this study a continuity equation based optical flow method is presented and results on 3D PET patient datasets for cardiac mo...

We present a two-dimensional information representation, where small but overlapping Gaussian kernels are used to encode the data in a matrix. Apart from points we apply this to constraints that restrict the solution to a linear subspace. A localised decoding scheme accurately extracts multiple solutions together with an estimate of the covariances. We employ the method in optical flow computat...

In this paper, we present a spatio-temporal feature representation and a probabilistic matching function to recognise lip movements from pronounced digits. Our model (1) automatically selects spatio-temporal features extracted from 10 digit model templates and (2) matches them with probe video sequences. Spatio-temporal features embed lip movements from pronouncing digits and contain more discr...

This paper presents a method for dense 4D temporal alignment of partial reconstructions of non-rigid surfaces observed from single or multiple moving cameras of complex scenes. 4D Match Trees are introduced for robust global alignment of non-rigid shape based on the similarity between images across sequences and views. Wide-timeframe sparse correspondence between arbitrary pairs of images is es...

In this paper a new robust estimator of the optical flow field is shown. Arising from the techniques based on the O.EC. (Optical Flow Constrain), we develop an estimation that takes several measures around a given pixel and discards the erroneous ones, using a voting schema. In this way, velocities that have more accumulated votes are taken as the correct ones. A preliminary comparison with oth...