17815340. OBJECT-DRIVEN EVENT DETECTION FROM FIXED CAMERAS IN EDGE ENVIRONMENTS simplified abstract (Dell Products L.P.)

From WikiPatents
Jump to navigation Jump to search

OBJECT-DRIVEN EVENT DETECTION FROM FIXED CAMERAS IN EDGE ENVIRONMENTS

Organization Name

Dell Products L.P.

Inventor(s)

Vinicius Michel Gottin of Rio de Janeiro (BR)

Pablo Nascimento Da Silva of Niteroi (BR)

Paulo Abelha Ferreira of Rio de Janeiro (BR)

OBJECT-DRIVEN EVENT DETECTION FROM FIXED CAMERAS IN EDGE ENVIRONMENTS - A simplified explanation of the abstract

This abstract first appeared for US patent application 17815340 titled 'OBJECT-DRIVEN EVENT DETECTION FROM FIXED CAMERAS IN EDGE ENVIRONMENTS

Simplified Explanation

Object driven event detection is a technology that identifies video frames of interest from camera streams in an environment and uses them along with node positions to detect events. The output of the detection model, combined with an event model, is used to make decisions and perform actions in the environment.

  • Video frames of interest are identified from camera streams in an environment.
  • Node positions for nodes in the area of coverage of the cameras are provided as input.
  • The video frames of interest and node positions are used in a detection module.
  • The output of the detection model is combined with the output of an event model.
  • A decision pipeline uses the combined output to make decisions and perform actions in the environment.

Potential applications of this technology:

  • Surveillance systems: The technology can be used to detect specific events or objects in video streams, enhancing the capabilities of surveillance systems.
  • Smart homes/buildings: It can be used to automate actions based on detected events, such as turning on lights when a person is detected in a room.
  • Traffic monitoring: The technology can be applied to detect traffic events, such as accidents or congestion, for efficient traffic management.

Problems solved by this technology:

  • Efficient event detection: The technology automates the process of identifying video frames of interest and detecting events, saving time and effort compared to manual monitoring.
  • Real-time decision making: By combining the output of the detection and event models, the technology enables real-time decision making and action execution based on the detected events.

Benefits of this technology:

  • Enhanced situational awareness: The technology provides a more comprehensive understanding of events happening in an environment by analyzing video frames and node positions.
  • Automation and efficiency: By automating event detection and decision making, the technology improves efficiency and reduces the need for manual intervention.
  • Improved security and safety: The technology can enhance security and safety by detecting and responding to events in real-time, such as intrusions or accidents.


Original Abstract Submitted

Object driven event detection is disclosed for nodes in an environment. Video frames of interest are identified from the video streams of cameras in the environment. The video frames of interest are input, along with node positions for nodes in the area of coverage of the cameras, into a detection module. The output of the detection model, combined with the output of an event model, are used by a decision pipeline to make decisions and perform actions in the environment.