20240046659. METHOD FOR DETECTING AN ENVIRONMENT BY MEANS OF IMAGES FROM AT LEAST TWO IMAGE SENSORS simplified abstract (Robert Bosch GmbH)

From WikiPatents
Jump to navigation Jump to search

METHOD FOR DETECTING AN ENVIRONMENT BY MEANS OF IMAGES FROM AT LEAST TWO IMAGE SENSORS

Organization Name

Robert Bosch GmbH

Inventor(s)

Tamas Kapelner of Hildesheim (DE)

METHOD FOR DETECTING AN ENVIRONMENT BY MEANS OF IMAGES FROM AT LEAST TWO IMAGE SENSORS - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240046659 titled 'METHOD FOR DETECTING AN ENVIRONMENT BY MEANS OF IMAGES FROM AT LEAST TWO IMAGE SENSORS

Simplified Explanation

The patent application describes a method for detecting an environment using images from at least two image sensors. The method involves providing a first image of the environment from a first image sensor and a second image from a second image sensor. The first and second image sensors have different detection ranges. A virtual surface is defined between the environment and the image sensors. A virtual overall image is generated on the virtual surface by projecting the pixels of the first and second images onto the virtual surface. The environment is represented based on the virtual overall image and a neural network trained to represent the environment.

  • The method involves using images from multiple image sensors with different detection ranges.
  • A virtual surface is defined to create a unified image of the environment.
  • The virtual overall image is generated by projecting the pixels of the first and second images onto the virtual surface.
  • The environment is represented using a neural network trained to represent the environment.
  • The method allows for the detection of the environment based on the virtual overall image.

Potential applications of this technology:

  • Surveillance systems: The method can be used in surveillance systems to detect and monitor environments using images from multiple sensors.
  • Autonomous vehicles: The technology can be applied in autonomous vehicles to detect and understand the surrounding environment for safe navigation.
  • Robotics: The method can be used in robotics to perceive and interact with the environment using images from multiple sensors.
  • Augmented reality: The technology can be utilized in augmented reality applications to overlay virtual objects onto the real environment.

Problems solved by this technology:

  • Improved environment detection: By using images from multiple sensors with different detection ranges, the method provides a more comprehensive and accurate representation of the environment.
  • Virtual surface creation: The defined virtual surface allows for the generation of a unified image, eliminating the need for complex image stitching techniques.
  • Neural network representation: The use of a trained neural network enables the accurate representation and understanding of the environment based on the virtual overall image.

Benefits of this technology:

  • Enhanced situational awareness: The method provides a more detailed and comprehensive understanding of the environment, improving situational awareness in various applications.
  • Improved object detection: By combining images from multiple sensors, the method enhances object detection capabilities, leading to improved safety and efficiency.
  • Simplified image processing: The virtual surface and projection transformation techniques simplify the image processing required to generate the virtual overall image.
  • Versatile applications: The technology can be applied in various fields, including surveillance, autonomous vehicles, robotics, and augmented reality, expanding its potential applications.


Original Abstract Submitted

a method for detecting an environment using images from at least two image sensors. the method includes: providing a first image of the environment from a first image sensor; providing a second image of the environment from a second image sensor; wherein the first image sensor and the second image sensor are configured to detect the environment with different detection ranges; defining a virtual surface, which is arranged between the environment and the at least two image sensors; generating a virtual overall image on the virtual surface based on a projection transformation of respective pixels of the first image and a projection transformation of respective pixels of the second image from a relevant image plane of the relevant image sensor onto the virtual surface; and representing the environment based on the virtual overall image and on a neural network trained to represent the environment, to detect the environment.

Retrieved from "http://wikipatents.org/index.php?title=20240046659._METHOD_FOR_DETECTING_AN_ENVIRONMENT_BY_MEANS_OF_IMAGES_FROM_AT_LEAST_TWO_IMAGE_SENSORS_simplified_abstract_(Robert_Bosch_GmbH)&oldid=32775"