17917332. FACILITATING ANNOTATION OF OBJECTS simplified abstract (Telefonaktiebolaget LM Ericsson (publ))

From WikiPatents
Jump to navigation Jump to search

FACILITATING ANNOTATION OF OBJECTS

Organization Name

Telefonaktiebolaget LM Ericsson (publ)

Inventor(s)

Thalanayar Muthukumar of PLANO TX (US)

Volodya Grancharov of SOLNA (SE)

Marc Couch of FRISCO TX (US)

FACILITATING ANNOTATION OF OBJECTS - A simplified explanation of the abstract

This abstract first appeared for US patent application 17917332 titled 'FACILITATING ANNOTATION OF OBJECTS

Simplified Explanation

The present disclosure describes a method and device for facilitating the annotation of an object in a sequence of images. The method involves marking the object in an image, performing edge detection on the marked object, suppressing visual data other than the object, and adjusting the position of the marking to align with the object in subsequent images.

  • The method helps in annotating objects in a sequence of images.
  • It involves marking the object in an image and performing edge detection on the marked object.
  • Visual data other than the object being annotated is suppressed to improve accuracy.
  • The position of the marking is adjusted to align with the object in subsequent images.

Potential Applications

  • This technology can be used in computer vision applications for object detection and tracking in video sequences.
  • It can be applied in autonomous vehicles for identifying and tracking objects on the road.
  • This method can be used in surveillance systems for monitoring and tracking specific objects or individuals.

Problems Solved

  • The method solves the problem of accurately annotating objects in a sequence of images.
  • It addresses the challenge of suppressing irrelevant visual data to improve the accuracy of object detection.
  • The method solves the problem of aligning the annotation with the object in subsequent images.

Benefits

  • The method simplifies the process of annotating objects in a sequence of images.
  • It improves the accuracy of object detection by suppressing irrelevant visual data.
  • The adjustment of the marking position ensures consistency in object annotation across multiple images.


Original Abstract Submitted

The present disclosure relates to a method of facilitating annotation of an object () in a sequence of images, and a device () performing the method. In a first aspect a method of facilitating annotation of an object () in a sequence of images is provided. The method comprises marking (S) the object () in an image in the sequence of images, performing (S) edge detection on the marked object () in the sequence of images, suppressing (S) visual data (, ) other than the object () being subjected to edge detection in the sequence of images, and adjusting (S) position of a marking () such that the marking is aligned with the object () being subjected to edge detection in subsequent images of the sequence.