17835310. SYSTEM AND METHOD FOR OCCLUSION RECONSTRUCTION IN SURROUND VIEWS USING TEMPORAL INFORMATION simplified abstract (GM Global Technology Operations LLC)

From WikiPatents
Jump to navigation Jump to search

SYSTEM AND METHOD FOR OCCLUSION RECONSTRUCTION IN SURROUND VIEWS USING TEMPORAL INFORMATION

Organization Name

GM Global Technology Operations LLC

Inventor(s)

Yehonatan Mandel of Herzliya (IL)

Michael Slutsky of Kefar-Saba (IL)

SYSTEM AND METHOD FOR OCCLUSION RECONSTRUCTION IN SURROUND VIEWS USING TEMPORAL INFORMATION - A simplified explanation of the abstract

This abstract first appeared for US patent application 17835310 titled 'SYSTEM AND METHOD FOR OCCLUSION RECONSTRUCTION IN SURROUND VIEWS USING TEMPORAL INFORMATION

Simplified Explanation

The patent application describes a system for reconstructing occlusions in surround views using temporal information. The system includes an active camera device and a computerized visual data controller.

  • The system analyzes image data from the camera to generate a three-dimensional representation of the operating environment.
  • It synthesizes a virtual camera view of the environment from a desired viewpoint.
  • It identifies occlusions in the virtual camera view.
  • It uses historical iterations of the image data to identify immobile objects in the environment.
  • It estimates filled information for the occlusions using the historical iterations.
  • It reconstructs the occlusions with the filled information using pixel data from the immobile objects.
  • It utilizes the representation of the environment to provide navigational guidance.

Potential applications of this technology:

  • Automotive industry: This system can be used in surround view systems for vehicles, providing drivers with a clear and accurate view of their surroundings, even when certain objects are obstructed.
  • Surveillance: The system can be used in surveillance cameras to reconstruct occluded areas and provide a complete view of the monitored environment.
  • Virtual reality: This technology can be applied in virtual reality systems to enhance the user's experience by reconstructing occluded objects or areas in the virtual environment.

Problems solved by this technology:

  • Occlusions in surround views can hinder situational awareness and navigation. This system solves the problem by reconstructing occlusions using historical iterations of image data.
  • Traditional methods of occlusion reconstruction may be computationally expensive or inaccurate. This system utilizes temporal information and immobile objects to estimate filled information for occlusions, improving accuracy and efficiency.

Benefits of this technology:

  • Improved situational awareness: By reconstructing occlusions, this system provides users with a more complete and accurate view of their surroundings, enhancing safety and navigation.
  • Cost-effective solution: By utilizing historical iterations of image data and immobile objects, this system reduces the need for complex and expensive hardware or additional sensors.
  • Real-time guidance: The system utilizes the representation of the environment to provide navigational guidance, helping users navigate through occluded areas more effectively.


Original Abstract Submitted

A system for occlusion reconstruction in surround views using temporal information is provided. The system includes an active camera device generating image data describing a first view of an operating environment and a computerized visual data controller. The controller includes programming to analyze the image data to generate a three-dimensional computerized representation of the operating environment, utilize the image data and the representation of the operating environment to synthesize a virtual camera view of the operating environment from a desired viewpoint, and identify an occlusion in the virtual camera view. The controller further includes programming to utilize historical iterations of the image data identify immobile objects within the operating environment and utilize the historical iterations to estimate filled information for the occlusion. The controller further includes programming to reconstruct the occlusion with the filled information using pixel data from the immobile objects and utilize the representation to provide navigational guidance.