FMODetect: Robust Detection of Fast Moving Objects

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F67985556%3A_____%2F21%3A00546470" target="_blank" >RIV/67985556:_____/21:00546470 - isvavai.cz</a>

Nalezeny alternativní kódy

RIV/68407700:21230/21:00354083

Výsledek na webu

<a href="http://dx.doi.org/10.1109/ICCV48922.2021.00352" target="_blank" >http://dx.doi.org/10.1109/ICCV48922.2021.00352</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/ICCV48922.2021.00352" target="_blank" >10.1109/ICCV48922.2021.00352</a>

Jazyk výsledku

angličtina

Název v původním jazyce

FMODetect: Robust Detection of Fast Moving Objects

Popis výsledku v původním jazyce

We propose the first learning-based approach for fast moving objects detection. Such objects are highly blurred and move over large distances within one video frame. Fastnmoving objects are associated with a deblurring and matting problem, also called deblatting. We show that the separation of deblatting into consecutive matting and deblurring allows achieving real-time performance, i.e. an order of magnitude speed-up, and thus enabling new classes of application. The proposed method detects fast moving objects as a truncated distance function to the trajectory by learning from synthetic data. For the sharp appearance estimation and accurate trajectory estimation, we propose a matting and fitting network that estimates the blurred appearance without background, followed by an energy minimization based deblurring. The state-of-the-art methods are outperformed in terms of recall, precision, trajectory estimation, and sharp appearance reconstruction. Compared to other methods, such as deblatting, the inference is of several orders of magnitude faster and allows applications such as real-time fast moving object detection and retrieval in large video collections.n

Název v anglickém jazyce

FMODetect: Robust Detection of Fast Moving Objects

Popis výsledku anglicky

We propose the first learning-based approach for fast moving objects detection. Such objects are highly blurred and move over large distances within one video frame. Fastnmoving objects are associated with a deblurring and matting problem, also called deblatting. We show that the separation of deblatting into consecutive matting and deblurring allows achieving real-time performance, i.e. an order of magnitude speed-up, and thus enabling new classes of application. The proposed method detects fast moving objects as a truncated distance function to the trajectory by learning from synthetic data. For the sharp appearance estimation and accurate trajectory estimation, we propose a matting and fitting network that estimates the blurred appearance without background, followed by an energy minimization based deblurring. The state-of-the-art methods are outperformed in terms of recall, precision, trajectory estimation, and sharp appearance reconstruction. Compared to other methods, such as deblatting, the inference is of several orders of magnitude faster and allows applications such as real-time fast moving object detection and retrieval in large video collections.n

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

20206 - Computer hardware and architecture

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

2021

Kód důvěrnosti údajů

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

Název statě ve sborníku

Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)

ISBN

978-1-6654-2812-5

ISSN

2380-7504

e-ISSN

2380-7504

Počet stran výsledku

9

Strana od-do

3541-3549

Název nakladatele

IEEE

Místo vydání

Piscataway

Místo konání akce

Piscataway (on-line)

Datum konání akce

11. 10. 2021

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

—