Object Tracking (Computer Vision)

Evidential modeling for pose estimation

by Fabio Cuzzolin

A Modular Implementation of Wii Remote Head Tracking for Virtual Reality

by Ryan Pavlik

Object Tracking using MACH filter and Optical Flow in Cluttered Scenes and Variable Lighting Conditions

by Waqar Shahid Qureshi

Four‐dimensional telomere analysis in recordings of living human cells acquired with Controlled Light Exposure Microscopy

by Winnok H. De Vos

W. De Vos, G. Joss, W. Haffmans, R. Hoebe, E. Manders and P. Van Oostveldt.
Journal of Microscopy 238(3), 254-264, 2010.

Telomeres are the complex end structures that confer functional integrity and positional stability to human... more Telomeres are the complex end structures that confer functional integrity and positional stability to human chromosomes. Telomere research has long been dominated by length measurements and biochemical analyses. Recently, interest has shifted towards the role of their three-dimensional organization and dynamics within the nuclear volume. In the mammalian interphase nucleus, there is increasing evidence for a telomeric configuration that is non-random and is cell cycle and cell type dependent. This has functional implications for genome stability. Objective and reproducible representation of the spatiotemporal organization of telomeres, under different experimental conditions, requires quantification by reliable automated image processing techniques. In this paper, we describe methods for quantitative telomere analysis in cell nuclei of living human cells expressing telomere-binding fusion proteins. We present a toolbox for determining telomere positions within the nucleus with subresolution accuracy and tracking telomeres in 4D controlled light exposure microscopy (CLEM) recordings. The use of CLEM allowed for durable imaging and thereby improved segmentation performance considerably. With minor modifications, the underlying algorithms can be expanded to the analysis of other intranuclear features, such as nuclear bodies or DNA double stranded break foci.

Controlled light exposure microscopy reveals dynamic telomere microterritories throughout the cell cycle

by Winnok H. De Vos

W. De Vos, R. Hoebe, G. Joss, W. Haffmans, S. Baatout, P. Van Oostveldt and E. Manders
Cytometry Part A 75(5), p428-439, 2009.

Telomeres are complex end structures that confer functional integrity and positional stability to human chromosomes.... more Telomeres are complex end structures that confer functional integrity and positional stability to human chromosomes. Despite their critical importance, there is no clear view on telomere organization in cycling human cells and their dynamic behavior throughout the cell cycle. We investigated spatiotemporal organization of telomeres in living human ECV-304 cells stably expressing telomere binding proteins TRF1 and TRF2 fused to mCitrine using four dimensional microscopy. We thereby made use of controlled light exposure microscopy (CLEM), a novel technology that strongly reduces photodamage by limiting excitation in parts of the image where full exposure is not needed. We found that telomeres share small territories where they dynamically associ- ate. These territories are preferentially positioned at the interface of chromatin domains. TRF1 and TRF2 are abundantly present in these territories but not firmly bound. At the onset of mitosis, the bulk of TRF protein dissociates from telomere regions, territories disintegrate and individual telomeres become faintly visible. The combination of stable cell lines, CLEM and cytometry proved essential in providing novel insights in compartment-based nuclear organization and may serve as a model approach for investigating telomere-driven genome-instability and studying long-term nuclear dynamics.

Increased plasticity of the nuclear envelope and hypermobility of telomeres due to the loss of A-type lamins

by Winnok H. De Vos

W. De Vos, F. Houben, R. A. Hoebe, R. Hennekam, B. Van Engelen, E. Manders, F. Ramaekers, J. Broers and P. Van Oostveldt
Biochimica et Biophysica Acta – General Subjects 1800(4), p. 448-458, 2010.

Background: The nuclear lamina provides structural support to the nucleus and has a central role in defining nuclear... more Background: The nuclear lamina provides structural support to the nucleus and has a central role in defining nuclear organization. Defects in its filamentous constituents, the lamins, lead to a class of diseases collectively referred to as laminopathies. On the cellular level, lamin mutations affect the physical integrity of nuclei and nucleo-cytoskeletal interactions, resulting in increased susceptibility to mechanical stress and altered gene expression. Methods: In this study we quantitatively compared nuclear deformation and chromatin mobility in fibroblasts from a homozygous nonsense LMNA mutation patient and a Hutchinson-Gilford progeria syndrome patient with wild type dermal fibroblasts, based on the visualization of mCitrine labeled telomere-binding protein TRF2 with light-economical imaging techniques and cytometric analyses. Results: Without application of external forces, we found that the absence of functional lamin A/C leads to increased nuclear plasticity on the hour and minute time scale but also to increased intranuclear mobility down to the second time scale. In contrast, progeria cells show overall reduced nuclear dynamics. Experimental manipulation (farnesyltransferase inhibition or lamin A/C silencing) confirmed that these changes in mobility are caused by abnormal or reduced lamin A/C expression. Conclusions: These observations demonstrate that A-type lamins affect both nuclear membrane and telomere dynamics. General Significance: Because of the pivotal role of dynamics in nuclear function, these differences likely contribute to or represent novel mechanisms in laminopathy development.

2D mapping of strongly deformable cell nuclei‐based on contour matching

by Winnok H. De Vos

J. De Vylder, W. De Vos, E. Manders and W. Philips.
Cytometry Part A, 79(7), 580-588, 2011.

The spatiotemporal dynamics of protein complexes and genome loci are functionally linked to cellular health status. To... more The spatiotemporal dynamics of protein complexes and genome loci are functionally linked to cellular health status. To study the inherent motion of subnuclear particles, it is essential to remove any superimposed component stemming from displacement and deformation of the nucleus. In this article, we propose a mapping of the nuclear interior, which is based on the deformation of the nuclear contour and has no shape constraints. This registration procedure enabled an accurate estimation of telomere mobility in living human cells undergoing dramatic nuclear deformations. Given the large variety of pathologies and cellular processes that are associated with strong nuclear shape changes, the contour mapping algorithm has generic value for improving the accuracy of mobility measurements of genome loci and intranuclear macromolecule complexes.

Online real boosting for object tracking under severe appearance changes and occlusion

by Li Xu

Automated Electrorotation: Dielectric Characterization of Living Cells by Real-time Motion Estimation

by Giovanni De Gasperis

Published in 'Measurement Science and Technology', 1998

Electrorotation (ROT) has been applied widely for determining the dielectric properties of cells (and bio-particles)... more Electrorotation (ROT) has been applied widely for determining the dielectric properties of cells (and bio-particles) with single-cell resolution. However a serious limitation of ROT has been the tedious manual measurements required. A new real-time PC-based machine vision algorithm and hardware implementation are presented that achieve measurements of cell rotational motion and analysis of ROT spectra. The system is equipped with a computer-controlled quadrature digital synthesizer and is capable of measuring a ROT spectrum of a single cell with the frequency range 1 kHz-200 MHz in less than 5 min, taking four measurement points per frequency decade. Laser tweezers are used to facilitate cell selection and positioning in order to maximize the flexibility and accuracy of the system. The performance of this system is characterized in terms of robustness, accuracy and linearity with respect to manual measurements of real spinning cells under the influence of a rotating electric field. The system is quite generally applicable to a wide variety of mammalian cell morphologies and optical appearances. Membrane capacitance values derived from automated ROT measurements averaged within 10% of those obtained from manual measurements.

Fusión de Datos Distribuida en Redes de Sensores Visuales Utilizando Sistemas Multi-Agente

by Federico Castanedo

Rastreamento Óptico para Sistemas de Realidade Virtual e Aumentada

by Luis Augusto Consularo

A Time-Triggered Object Tracking Subsystem for Advanced Driver Assistance Systems

by Wilfried Elmenreich

Multi-sensor object tracking is an important feature for advanced driver assistance systems in future automobiles.... more Multi-sensor object tracking is an important feature for advanced driver assistance systems in future automobiles. Most state-of-the-art systems cannot guarantee deterministic processing of the sensor values due to unsynchronized sensing and processing units. To overcome this shortcoming we propose a paradigm shift towards a time-triggered system architecture providing a deterministic bus system, synchronized nodes, and a global time-base. The paradigm shift is supported by results of a simulation of different synchronization and scheduling approaches which suggest that although non-time-triggered approaches perform well in scenarios with low process noise, the time-triggered model becomes advantageous in potentially dangerous scenarios with high dynamics. In order to validate the results of the simulation for real life scenarios, we analyzed test drives derived from a testbed featuring a Volkswagen Touran being equipped with a laser scanner, a stereo camera system, a FlexRay communication system, an object tracking subsystem and a differential GPS system as reference.

A Synergistic Detection-and Track-Level System for Monitoring People In Smart Spaces

by Aristodemos Pnevmatikakis

Technical report

Robust tracking of multiple interacting people in indoors settings is of paramount importance for surveillance,... more Robust tracking of multiple interacting people in indoors settings is of paramount importance for surveillance, human-machine interfaces and assistive living applications. The current approaches of extracting and modeling foreground body blobs fall short in resolving people in the camera views. We work around this problem by utilizing faces found in the body blobs. We propose a synergistic system of detectors and trackers. A robust foreground segmentation system gives body blobs, inside which, detectors locate faces. Since the pose of the faces is arbitrary, the detectors suffer from false positives and misses. The former are alleviated by a composite detection validation scheme based on Gaussian Mixture modeling of face properties and classification of color histograms by subclass Linear Discriminant Analysis. The misses are filled in by the use of trackers between detections. We evaluate three different trackers (CAM-Shift, Kalman filters and particle filters) using five recordings from four cameras of people moving in a meeting room, totaling 100 minutes of video, showing a relative tracking accuracy increase by 15% over earlier systems. If multiple cameras monitor the same space, then the system can be extended to three dimensions by associating the face tracks of the different camera views.

Moving Object Tracking In H. 264/AVC Bitstream

by Wonsang You

published in Lecture Notes in Computer Science, 2007. For more information, refer to the link: https://sites.google.com/site/wsgyou/research/livevideo.

Data broadcasting services are required to provide user interactivity through connecting additional contents such as... more Data broadcasting services are required to provide user interactivity through connecting additional contents such as object information to audio-visual contents. H.264/AVC-based metadata authoring tools include functions which identify and track position and motion of objects. In this work, we propose a method for tracking the target object by using partially decoded texture data and motion vectors extracted directly from H.264/AVC bitstream. This method achieves low computational complexity and high performance through the dissimilarity energy minimization algorithm which tracks feature points adaptively according to these characteristics. The experiment has shown that the proposed method had high performance with fast processing time.

Real-Time Detection and Tracking of Multiple Objects With Partial Decoding In H. 264/AVC Bitstream Domain

by Wonsang You

published in Proceedings of SPIE, 2009. The LiveVideo, an open-source real-time video analysis software which had been applied for this article, can be downloaded from https://sourceforge.net/projects/livevideo/.

In this paper, we show that we can apply probabilistic spatiotemporal macroblock filtering (PSMF) and partial decoding... more In this paper, we show that we can apply probabilistic spatiotemporal macroblock filtering (PSMF) and partial decoding processes to effectively detect and track multiple objects in real time in H.264|AVC bitstreams with stationary background. Our contribution is that our method cannot only show fast processing time but also handle multiple moving objects that are articulated, changing in size or internally have monotonous color, even though they contain a chaotic set of non-homogeneous motion vectors inside. In addition, our partial decoding process for H.264|AVC bitstreams enables to improve the accuracy of object trajectories and overcome long occlusion by using extracted color information.