18460014. SYSTEMS AND METHODS FOR AUTOMATED OBJECT RECOGNITION simplified abstract (Capital One Services, LLC)

From WikiPatents
Jump to navigation Jump to search

SYSTEMS AND METHODS FOR AUTOMATED OBJECT RECOGNITION

Organization Name

Capital One Services, LLC

Inventor(s)

Hannes Mikael Jouhikainen of McLean VA (US)

Drew Jacobs of Alameda CA (US)

SYSTEMS AND METHODS FOR AUTOMATED OBJECT RECOGNITION - A simplified explanation of the abstract

This abstract first appeared for US patent application 18460014 titled 'SYSTEMS AND METHODS FOR AUTOMATED OBJECT RECOGNITION

Simplified Explanation

The patent application describes a method for recognizing objects in a video stream using machine learning algorithms.

  • The method receives a video stream from a source and selects specific frames at a certain rate.
  • The selected frames are divided into image blocks.
  • The machine learning algorithm determines an image recognition parameter to identify image blocks containing an object.
  • A likelihood metric is calculated based on the frame selection rate to determine if an image block corresponds to the object.
  • Information identifying the object is displayed on a display.

Potential Applications

This technology has potential applications in various fields, including:

  • Surveillance systems: It can be used to identify specific objects or individuals in video footage, enhancing security measures.
  • Autonomous vehicles: The method can help vehicles recognize and track objects in real-time, improving safety and navigation.
  • Augmented reality: It can be utilized to identify and overlay digital information on real-world objects in real-time.

Problems Solved

The method addresses the following problems:

  • Object recognition in video streams: It provides a solution for accurately identifying objects in a continuous video stream.
  • Efficient processing: By selecting frames at a certain rate, it reduces computational resources required for object recognition.
  • Real-time identification: The method enables real-time identification of objects, allowing for immediate action or response.

Benefits

The technology offers several benefits, including:

  • Improved accuracy: By utilizing machine learning algorithms, it enhances the accuracy of object recognition in video streams.
  • Resource efficiency: The frame selection rate optimizes computational resources, making the method more efficient.
  • Real-time response: The ability to identify objects in real-time enables immediate action or response based on the recognized objects.


Original Abstract Submitted

A method for recognizing an object in a video stream may include receiving a video stream comprising a plurality of video frames from a video source. The method may also select at least one video frame from the video frames according to a frame selection rate. The method may also partition the selected video frame into a first plurality of image blocks, and recognize, out of the first plurality of image blocks, a second plurality of image blocks which comprise an image of an object, the recognition being based on an image recognition parameter determined by a machine-learning algorithm. The method may also determine that at least one of the second plurality of image blocks corresponds to the object based on a likelihood metric, the likelihood metric being determined by the processor based on at least the frame selection rate, and display, on a display, information identifying the object.