Verfahren zur Verbesserung der Objekterkennung in Hochauflösenden Sichtsystemen

Details

Veröffentlichungs-Nr.

EP4787334

Anmeldetag

2. Februar 2026

Veröffentlichung

5. August 2026

Rechtsraum

EP

Abstract

A vision system and method may include an image sensor configured to capture an image having a first resolution of a scene in which multiple objects are captured in the image. The image may be at a first analysis level and each of the objects are associated with an object class. Computing device(s) may be in electrical communication with the image sensor, and be configured to generate additional image(s) having respective lower resolutions. Each of the additional image(s) being at at least one second analysis level. A map that associates the object class(es) with one or more different analysis levels may be used to indicate which of the object class(es) to identify at the corresponding analysis levels. A multiclass classifier may be executed for each of the corresponding analysis levels to identify objects within the respective images. A list derived from the identified objects may be formed and output.

Anmelder

Firma

Datalogic IP Tech S.r.l.

Land

🇮🇹 Italien