MONOCULAR-VISION-BASED DETECTION OF MOVING OBJECTS

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F23%3A00373074" target="_blank" >RIV/68407700:21230/23:00373074 - isvavai.cz</a>

Výsledek na webu

<a href="https://worldwide.espacenet.com/patent/search/family/078414437/publication/EP4174770B1?q=pn%3DEP4174770B1" target="_blank" >https://worldwide.espacenet.com/patent/search/family/078414437/publication/EP4174770B1?q=pn%3DEP4174770B1</a>

DOI - Digital Object Identifier

—

Jazyk výsledku

angličtina

Název v původním jazyce

MONOCULAR-VISION-BASED DETECTION OF MOVING OBJECTS

Popis výsledku v původním jazyce

Systems and methods detect moving objects in image data of a monocular video stream using a trained CNN-based object-feature extractor (2) and a trained CNN-based motion-feature extractor (4) operating in parallel branches on the input video stream, with the feature sets produced by the features extractors being concatenated and supplied to a detection head (6). The object-feature extractor (2) is trained to generate output comprising class-agnostic features. The motion-feature extractor (4) is trained to generate output including first (backward) motion-features (Mt―1) relating to motion between a subject image frame and the previous image frame and second (forward) motion-features (Mt+1) relating to motion between the subject image frame and the next image frame, based on respective backward and forward motion cost volumes.

Název v anglickém jazyce

MONOCULAR-VISION-BASED DETECTION OF MOVING OBJECTS

Popis výsledku anglicky

Systems and methods detect moving objects in image data of a monocular video stream using a trained CNN-based object-feature extractor (2) and a trained CNN-based motion-feature extractor (4) operating in parallel branches on the input video stream, with the feature sets produced by the features extractors being concatenated and supplied to a detection head (6). The object-feature extractor (2) is trained to generate output comprising class-agnostic features. The motion-feature extractor (4) is trained to generate output including first (backward) motion-features (Mt―1) relating to motion between a subject image frame and the previous image frame and second (forward) motion-features (Mt+1) relating to motion between the subject image frame and the next image frame, based on respective backward and forward motion cost volumes.

Druh

P - Patent

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

—

Návaznosti

S - Specificky vyzkum na vysokych skolach

Rok uplatnění

2023

Kód důvěrnosti údajů

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

Číslo patentu nebo vzoru

EP4174770

Vydavatel

EPO_1 -

Název vydavatele

European Patent Office

Místo vydání

Munich, The Hague, Berlin, Vienna, Brussels

Stát vydání

—

Datum přijetí

29. 11. 2023

Název vlastníka

TOYOTA MOTOR CO LTD [JP]; CZECH TECHNICAL UNIVERSITY IN PRAGUE [CZ]

Způsob využití

A - Výsledek využívá pouze poskytovatel

Druh možnosti využití

A - K využití výsledku jiným subjektem je vždy nutné nabytí licence