17698445. METHOD AND APPARATUS FOR DETECTING OBJECT IN IMAGE simplified abstract (Samsung Electronics Co., Ltd.)

From WikiPatents
Jump to navigation Jump to search

METHOD AND APPARATUS FOR DETECTING OBJECT IN IMAGE

Organization Name

Samsung Electronics Co., Ltd.

Inventor(s)

Kikyung Kim of Hwaseong-si (KR)

INSOO Kim of Seongnam-si (KR)

JIWON Baek of Hwaseong-si (KR)

SEUNGJU Han of Seoul (KR)

JAEJOON Han of Seoul (KR)

METHOD AND APPARATUS FOR DETECTING OBJECT IN IMAGE - A simplified explanation of the abstract

This abstract first appeared for US patent application 17698445 titled 'METHOD AND APPARATUS FOR DETECTING OBJECT IN IMAGE

Simplified Explanation

The abstract describes a method for object detection using an object detection apparatus. Here is a simplified explanation of the abstract:

  • The object detection apparatus receives an input image.
  • It uses an object detection model to detect a target candidate object from the input image.
  • It also uses an error prediction model to detect an error object from the input image.
  • Based on the results of detecting the target candidate object and the error object, the apparatus detects a target object in the input image.

Potential applications of this technology:

  • Surveillance systems: The object detection method can be used in surveillance systems to detect and track specific objects or individuals.
  • Autonomous vehicles: This method can be applied in autonomous vehicles to detect and identify objects on the road, such as pedestrians, vehicles, or obstacles.
  • Robotics: The object detection method can be used in robotics to enable robots to identify and interact with objects in their environment.

Problems solved by this technology:

  • Accurate object detection: The use of both an object detection model and an error prediction model improves the accuracy of detecting target objects in an image.
  • Error detection: The method also detects error objects, which can help in identifying false positives or errors in the object detection process.

Benefits of this technology:

  • Improved object detection accuracy: By combining the results of the object detection model and the error prediction model, the method enhances the accuracy of detecting target objects.
  • Error identification: The method helps in identifying errors or false positives in the object detection process, leading to more reliable results.
  • Versatility: The object detection method can be applied in various fields, such as surveillance, autonomous vehicles, and robotics, making it a versatile solution.


Original Abstract Submitted

An object detection method performed by an object detection apparatus, includes receiving an input image, obtaining, using an object detection model, a result of detecting a target candidate object from the input image, obtaining, using an error prediction model, a result of detecting an error object from the input image, and detecting a target object in the input image based on the result of detecting the target candidate object and the result of detecting the error object.