Abstract.Where feature points are used in real-time frame-rate applications, a high-speed feature detector is necessary. Feature detectors such as SIFT (DoG), Harris and SUSAN are good methods which yield high quality features, however they are too computationally intensive for use in real-time applications of any complexity. Here we show that machine learning can be used to derive a feature detector which can fully process live PAL video using less than 7% of the available processing time. By comparison neither the Harris detector (120%) nor the detection stage of SIFT (300%) can operate at full frame rate.Clearly a high-speed detector is of limited use if the features produced are unsuitable for downstream processing. In particular, the same scene viewed from two different positions should yield features which correspond to the same real-world 3D locations [1]. Hence the second contribution of this paper is a comparison corner detectors based on this criterion applied to 3D scenes. This comparison supports a number of claims made elsewhere concerning existing corner detectors. Further, contrary to our initial expectations, we show that despite being principally constructed for speed, our detector significantly outperforms existing feature detectors according to this criterion.

The repeatability and efficiency of a corner detector determines how likely it is to be useful in a real-world application. The repeatability is important because the same scene viewed from different positions should yield features which correspond to the same real-world 3D locations. The efficiency is important because this determines whether the detector combined with further processing can operate at frame rate. Three advances are described in this paper. First, we present a new heuristic for feature detection and, using machine learning, we derive a feature detector from this which can fully process live PAL video using less than 5 percent of the available processing time. By comparison, most other detectors cannot even operate at frame rate (Harris detector 115 percent, SIFT 195 percent). Second, we generalize the detector, allowing it to be optimized for repeatability, with little loss of efficiency. Third, we carry out a rigorous comparison of corner detectors based on the above repeatability criterion applied to 3D scenes. We show that, despite being principally constructed for speed, on these stringent tests, our heuristic detector significantly outperforms existing feature detectors. Finally, the comparison demonstrates that using machine learning produces significant improvements in repeatability, yielding a detector that is both very fast and of very high quality.

No abstract

We demonstrate a localization microscopy analysis method that is able to extract results in live cells using standard fluorescent proteins and Xenon arc lamp illumination. Our Bayesian analysis of blinking and bleaching (3B analysis) method models the entire dataset simultaneously as being generated by a number of fluorophores which may or may not be emitting light at any given time. The resulting technique allows many overlapping fluorophores in each frame, and unifies the analysis of localization from blinking and bleaching events. By modeling the entire dataset we are able to use each reappearance of a fluorophore to improve the localization accuracy. The high performance of this technique allows us to reveal the nanoscale dynamics of podosome formation and dissociation with a resolution of 50 nm on a four second timescale.

SUMMARYThe pioneering cell biologist Michael Abercrombie first described the process of contact inhibition of locomotion more than 50 years ago when migrating fibroblasts were observed to rapidly change direction and migrate away upon collision. Since then, we have gleaned little understanding of how contact inhibition is regulated and only lately observed its occurrence in vivo. We recently revealed that Drosophila macrophages (haemocytes) require contact inhibition for their uniform embryonic dispersal. Here, to investigate the role that contact inhibition plays in the patterning of haemocyte movements, we have mathematically analysed and simulated their contact repulsion dynamics. Our data reveal that the final pattern of haemocyte distribution, and the details and timing of its formation, can be explained by contact inhibition dynamics within the geometry of the Drosophila embryo. This has implications for morphogenesis in general as it suggests that patterns can emerge, irrespective of external cues, when cells interact through simple rules of contact repulsion.