Tracking-Learning-Detection

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F12%3A00200439" target="_blank" >RIV/68407700:21230/12:00200439 - isvavai.cz</a>

Výsledek na webu

<a href="http://dx.doi.org/10.1109/TPAMI.2011.239" target="_blank" >http://dx.doi.org/10.1109/TPAMI.2011.239</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/TPAMI.2011.239" target="_blank" >10.1109/TPAMI.2011.239</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Tracking-Learning-Detection

Popis výsledku v původním jazyce

This paper investigates long-term tracking of unknown objects in a video stream. The object is defined by its location and extent in a single frame. In every frame that follows, the task is to determine the object?s location and extent or indicate that the object is not present. We propose a novel tracking framework (TLD) that explicitly decomposes the long-term tracking task into tracking, learning, and detection. The tracker follows the object from frame to frame. The detector localizes all appearances that have been observed so far and corrects the tracker if necessary. The learning estimates the detector?s errors and updates it to avoid these errors in the future. We study how to identify the detector?s errors and learn from them. We develop a novel learning method (P-N learning) which estimates the errors by a pair of ?experts?: 1) P-expert estimates missed detections, and 2) N-expert estimates false alarms. The learning process is modeled as a discrete dynamical system and the co

Název v anglickém jazyce

Tracking-Learning-Detection

Popis výsledku anglicky

This paper investigates long-term tracking of unknown objects in a video stream. The object is defined by its location and extent in a single frame. In every frame that follows, the task is to determine the object?s location and extent or indicate that the object is not present. We propose a novel tracking framework (TLD) that explicitly decomposes the long-term tracking task into tracking, learning, and detection. The tracker follows the object from frame to frame. The detector localizes all appearances that have been observed so far and corrects the tracker if necessary. The learning estimates the detector?s errors and updates it to avoid these errors in the future. We study how to identify the detector?s errors and learn from them. We develop a novel learning method (P-N learning) which estimates the errors by a pair of ?experts?: 1) P-expert estimates missed detections, and 2) N-expert estimates false alarms. The learning process is modeled as a discrete dynamical system and the co

Druh

J_x - Nezařazeno - Článek v odborném periodiku (Jimp, Jsc a Jost)

CEP obor

JD - Využití počítačů, robotika a její aplikace

OECD FORD obor

—

Projekt

Výsledek vznikl pri realizaci vícero projektů. Více informací v záložce Projekty.

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2012

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

IEEE Transactions on Pattern Analysis and Machine Intelligence

ISSN

0162-8828

e-ISSN

—

Svazek periodika

34

Číslo periodika v rámci svazku

7

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

14

Strana od-do

1409-1422

Kód UT WoS článku

000304138300012

EID výsledku v databázi Scopus

—