In this paper, we propose a new feature subset evaluation method for feature selection in object tracking. According to the fact that a feature which is useless by itself could become a good one when it is used together with some other features, we propose to evaluate feature subsets as a whole for object tracking instead of scoring each feature individually and find out the most distinguishabl...

In this paper we propose a new approach for tracking manoeuvring objects using variable rate particle filters with multiple sensors. Unlike other approaches the proposed method assumes that the states change at different and unknown rates compared with the observation process, and hence is able to model parsimoniously the manoeuvring behaviours of an object. Furthermore, Poisson model is used t...

We present a near realtime text tracking system capable of detecting and tracking text on outdoor shop signs or indoor notices, at rates of up to 15 frames per second (for generous 640× 480 images), depending on scene complexity. The method is based on extracting text regions using a novel tree-based connected component filtering approach, combined with the Eigen-Transform texture descriptor. T...

Abstract The method of iterative particle reconstruction (IPR), introduced by Wieneke (Meas Sci Technol 24:024008, 2013), constitutes a major step toward Lagrangian tracking in densely seeded flows (Schanz et al. Exp Fluids 57:1–27, 2016). Here we present novel approaches several key aspects the algorithm, which, combination, triple working range IPR terms image densities. updated is proven to ...

We demonstrate a Bayesian approach to tracking and characterizing colloidal particles from in-line digital holograms. We model the formation of the hologram using Lorenz-Mie theory. We then use a tempered Markov-chain Monte Carlo method to sample the posterior probability distributions of the model parameters: particle position, size, and refractive index. Compared to least-squares fitting, our...

Automatic segmentation of spinal nerve bundles that originate within the dural sac and exit the spinal canal is important for diagnosis and surgical planning. The variability in intensity, contrast, shape and direction of nerves seen in high resolution myelographic MR images makes segmentation a challenging task. In this paper, we present an automatic tracking method for nerve segmentation base...

Accurate estimation of the axial position of a molecule using a single lateral image remains a challenge in fluorescent single particle tracking. Here, a principled algorithm for the Bayesian estimation of the axial position of a molecule in three-dimensional astigmatism-based particle tracking is proposed. This technique uses the data from a calibration image set to derive the position without...

The onset of transient Soret-driven convection is investigated experimentally in a colloidal suspension of thermosensitive nanoparticles by the shadowgraph technique and by particle tracking observations. From the shadowgraph images, the concentration profile is reconstructed, giving evidence of a convective motion inside the transient boundary layer. Furthermore, the latency times for the conv...

Efficient and accurate methods are needed to move agents (particles with behavior rules) through their environments. To support such applications, this paper presents a compact software architecture that can be used to interface parallel particle tracking software to computational mesh management systems. The in-element particle tracking framework supported by this software architecture is pres...