A novel scheme is proposed for the efficient object tracking by using partial projections of a sparse set of pixels to eigenspaces. This paper shows a theoretical framework of the sparse eigentemplate matching and its application to a real-time face tracker. The sparse eigentemplate matching is formalized as a partial projection onto an eigenspace. Only using a small number of pixels, it facili...

This paper details a method of determining the uncertainty of dimensional measurement for a three dimensional coordinate measurement machine. An experimental procedure was developed to compare three dimensional coordinate measurements with calibrated reference points. The reference standard used to calibrate these reference points was a fringe counting interferometer with the multilateration te...

Tracked objects rarely move alone. They are often temporarily accompanied by other objects undergoing similar motion. We propose a novel tracking algorithm called Sputnik Tracker. It is capable of identifying which image regions move coherently with the tracked object. This information is used to stabilize tracking in the presence of occlusions or fluctuations in the appearance of the tracked o...

In the last decade, significant progress has been made on developing automatic farfield tracking systems. The PETS 2007 dataset provides some interesting event detection challenges. In this paper, we describe a method of bootstrapping a background model in the presence of significant lighting changes. We then use a blob tracker as an attention mechanism for finding tracks of interest, which we ...

This paper presents a hybrid dialog state tracker that combines a rule based and a machine learning based approach to belief state tracking. Therefore, we call it a hybrid tracker. The machine learning in our tracker is realized by a Long Short Term Memory (LSTM) network. To our knowledge, our hybrid tracker sets a new state-of-the-art result for the Dialog State Tracking Challenge (DSTC) 2 dat...

The CMS Silicon Strip Tracker, referred from here on as the Tracker, was commissioned using cosmic muons in two main setups: the Magnet Test Cosmic Challenge (MTCC) and the Tracker Integration Facility (TIF). A large number of studies of the tracker performance and offline data analysis has been performed and many others are still ongoing. Only few of these studies for both setups are presented...

Tracking multiple objects in surveillance scenarios face considerable difficulty in handling occlusions. We report a composite tracker based on feature tracking and colour based tracking that demonstrates superior performance under high degrees of occlusion. Disjoint foreground blobs are extracted by using change masks obtained by combining an online-updated background model and flow informatio...

The main subsystems of the CMS Tracker have been assembled together in a dedicated large clean room at CERN, prior to the installation in CMS. Following the integration of the Tracker a long commissioning period took place, during which, up to 15% of the silicon modules were operated and read out simultaneously at different temperatures. Some of the achievements of this commissioning phase are ...

Der Kanade-Lucas-Tomasi (KLT) Tracker ist ein etabliertes Verfahren zur Bewegungsanalyse bzw. Bewegungskorrektur einer Kamera auf Oberflächen. Derartige Systeme, die auf dem KLT Tracker beruhen, finden vermehrt auch in medizintechnischen Szenarien ihren Einsatz. So ist die Frage wichtig, ob diese Methode auch auf relativ kontrastarmen Oberflächen wie menschlichem Gewebe, und hier insbesondere K...