Facial-sketch Synthesis: A New Challenge

Machine Intelligence Research - This paper aims to conduct a comprehensive study on facial-sketch synthesis (FSS). However, due to the high cost of obtaining hand-drawn sketch datasets, there is a...     

Editorial: Special Issue on “Texture Analysis and Synthesi”

International Journal of Computer Vision -     

Affine reconstruction from perspective image pairs with a relativeobject-camera translation in between

A method is described to recover the three-dimensional affine structure of a scene consisting of at least five points identified in two perspective views with a relative object-camera translation in between. When compared to the results for arbitrary stereo views, a more detailed reconstruction is possible using less information. The method presented only assumes that the two images are obtained by identical cameras, but no knowledge about the intrinsic parameters of the camera(s) or about the performed translation is assumed. By the same method, affine 3D reconstruction from a single view can be achieved for parallel structures. In that case, four points suffice for affine reconstruction     

CD57+/CD28- T cells in untreated hemato-oncological patients are expanded and display a Th1-type cytokine secretion profile, ex vivo cytolytic activity and enhanced tendency to apoptosis

Protopolystoma (Monogenea, Polystomatidae) is strictly specific to the anuran amphibian genus Xenopus. The host group is characterised by a polyploid series in which chromosome numbers reflect diploid, tetraploid, octoploid and dodecaploid constitutions; the series is considered to have evolved through interspecies hybridisation and genome duplication. This study correlates information on host evolutionary relationships with patterns of parasite speciation and host specificity. Protopolystoma is restricted to one subgenus (Xenopus) with multiples of 36 chromosomes, and is absent from the subgenus Silurana (with multiples of 20 chromosomes). Molecular, biochemical and karyotype evidence distinguishes three subgroups within Xenopus. Representative species from each subgroup, Xenopus muelleri, Xenopus fraseri and Xenopus laevis, have been examined for polystomatid infection. Two species of Protopolystoma occur in each of these host species. In X. muelleri, the two Protopolystoma species reflect parasite co-speciation corresponding with the divergence of two sibling host species. Xenopus fraseri and X. laevis (both with 2n = 36 chromosomes) are implicated in the hybrid origin of two octoploid species, Xenopus wittei and Xenopus vestitus (both 2n = 72). The relationships of the Protopolystoma species in these Xenopus taxa reflect this presumed ancestry. Xenopus wittei carries two species of Protopolystoma, one shared with X. fraseri and the other shared with X. laevis. Xenopus vestitus carries a single species of Protopolystoma which is shared with X. laevis but there is no "heirloom" which reflects its hybrid origin involving X. fraseri. In addition to these shared parasite species which may reflect shared host genes, X. fraseri and X. laevis each carry separate species-specific Protopolystoma which do not occur in other Xenopus species even where there is evidence of common genetic information (as in the allopolyploid wittei and vestitus). This case study may be interpreted as indicating a powerful influence of host genetic factors on susceptibility to infection, host-specificity, and parasite speciation.     

Multi-object tracking evaluated on sparse events

This article presents a visual object tracking method and applies an event-based performance evaluation metric for assessment. The proposed monocular object tracker is able to detect and track multiple object classes in non-controlled environments. The tracking framework uses Bayesian per-pixel classification to segment an image into foreground and background objects, based on observations of object appearances and motions in real-time. Furthermore, a performance evaluation method is presented and applied to different state-of-the-art trackers based on successful detections of semantically high level events. These events are extracted automatically from the different trackers an their varying types of low level tracking results. Then, a general new event metric is used to compare our tracking method with the other tracking methods against ground truth of multiple public datasets.     

Real-time range acquisition by adaptive structured light

The goal of this paper is to provide a "self-adaptive" system for real-time range acquisition. Reconstructions are based on a single frame structured light illumination. Instead of using generic, static coding that is supposed to work under all circumstances, system adaptation is proposed. This occurs on-the-fly and renders the system more robust against instant scene variability and creates suitable patterns at startup. A continuous trade-off between speed and quality is made. A weighted combination of different coding cues - based upon pattern color, geometry, and tracking - yields a robust way to solve the correspondence problem. The individual coding cues are automatically adapted within a considered family of patterns. The weights to combine them are based on the average consistency with the result within a small time-window. The integration itself is done by reformulating the problem as a graph cut. Also, the camera-projector configuration is taken into account for generating the projection patterns. The correctness of the range maps is not guaranteed, but an estimation of the uncertainty is provided for each part of the reconstruction. Our prototype is implemented using unmodified consumer hardware only and, therefore, is cheap. Frame rates vary between 10 and 25 fps, dependent on scene complexity.     

Reconstructing 3D trajectories of independently moving objects using generic constraints

The 3D reconstruction of scenes containing independently moving objects from uncalibrated monocular sequences still poses serious challenges. Even if the background and the moving objects are rigid, each reconstruction is only known up to a certain scale, which results in a one-parameter family of possible, relative trajectories per moving object with respect to the background. In order to determine a realistic solution from this family of possible trajectories, this paper proposes to exploit the increased linear coupling between camera and object translations that tends to appear at false scales. An independence criterion is formulated in the sense of true object and camera motions being minimally correlated. The increased coupling at false scales can also lead to the destruction of special properties such as planarity, periodicity, etc. of the true object motion. This provides us with a second, ‘non-accidentalness’ criterion for the selection of the correct motion among the one-parameter family.