RESUMO
We propose a method, with minimal bias caused by user input, to quickly detect and measure the nanocrystal size distribution from transmission electron microscopy (TEM) images using a combination of Laplacian of Gaussian filters and non-maximum suppression. We demonstrate the proposed method on bright-field TEM images of an a-SiC:H sample containing embedded silicon nanocrystals with varying magnifications and we compare the accuracy and speed with size distributions obtained by manual measurements, a thresholding method and PEBBLES. Finally, we analytically consider the error induced by slicing nanocrystals during TEM sample preparation on the measured nanocrystal size distribution and formulate an equation to correct this effect.
RESUMO
Model-free trackers can track arbitrary objects based on a single (bounding-box) annotation of the object. Whilst the performance of model-free trackers has recently improved significantly, simultaneously tracking multiple objects with similar appearance remains very hard. In this paper, we propose a new multi-object model-free tracker (using a tracking-by-detection framework) that resolves this problem by incorporating spatial constraints between the objects. The spatial constraints are learned along with the object detectors using an online structured SVM algorithm. The experimental evaluation of our structure-preserving object tracker (SPOT) reveals substantial performance improvements in multi-object tracking. We also show that SPOT can improve the performance of single-object trackers by simultaneously tracking different parts of the object. Moreover, we show that SPOT can be used to adapt generic, model-based object detectors during tracking to tailor them towards a specific instance of that object.
